DeskGPU
English

NVIDIA GeForce GTX 1650: which LLMs can it run?

This page was written and translated automatically by AI and checked by software against its sources, with no human editing. Specifications come from the sources listed; memory requirements and speeds are estimates calculated with published formulas. How we use AI

Specifications are for the 2019 version (TU117-300, GDDR5); other versions sold under the same name are not covered.

NVIDIA GeForce GTX 1650 has 4 GB of memory (manufacturer figure). Below, every model in the database is checked against it with llama.cpp at a context length of 8,192 tokens (or the model’s maximum if shorter).

Values updated Oct 19, 2026

Specifications

Memory (manufacturer figure)
4 GB
Memory type
GDDR5
Memory bus width
128 bit
Memory bandwidth
128 GB/s
Board power (TDP)
75 W
FP16 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
BF16 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
FP8 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
FP4 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
INT8 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
Interface
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.

Each value lists every source with its own figure; units have been normalized. A manufacturer’s “GB” of GPU memory is counted as GiB (2³⁰ bytes), which is also how AMD’s ROCm table states it. How specifications are checked

Run profile

Run profile: llama.cpp, CUDA back end (NVIDIA discrete GPU), all layers on the GPU, Flash Attention on, micro-batch (-ub) 512, F16 KV cache, context (-c) as shown; “Fits” is judged with llama-server’s default 4 parallel sequences (-np auto, unified KV cache) and “Doesn’t fit” with 1 sequence; idle GPU with no other programs using its memory.

After setting aside the memory this profile reserves, less than 2 GiB is left on this GPU, which is below this site’s threshold for judging. “Fits” and “Tight” are therefore not judged: a model is shown as “Doesn’t fit” only if it is too big even for the full memory; otherwise the result is “Unknown” with the memory needed.

Memory used for “Doesn’t fit” (C_high): the full 4 GiB per card. Run profiles and their measurements

Which models fit

“Fits” means llama.cpp's default --fit load check would place all layers on the GPU: our estimate of llama.cpp's buffers, plus its error margin, plus llama.cpp's 1 GiB per-card reserve, is within the memory counted as available. It does not promise that peak memory while generating fits. How results are decided

Models that don’t fit on one NVIDIA GeForce GTX 1650

Context 8,192 tokens. Even the lowest quantization does not fit on one card; the requirement shown is for that quantization.
Model Parameters Smallest quantization Available memory needed for “Fits” Several identical cards Result
granite-guardian-3.2-8b-factuality-detection 8.2B Q2_K 5.6 GiB — Doesn't fit
granite-3.3-8b-instruct 8.2B Q2_K 5.6 GiB — Doesn't fit
Phi-3.5-mini-instruct 3.8B IQ2_M 5.7 GiB — Doesn't fit
granite-4.2-8b 8.8B Q2_K 5.8 GiB — Doesn't fit
granite-guardian-4.1-8b 8.4B Q2_K 5.8 GiB — Doesn't fit
Mellum2-12B-A2.5B-Base 12.1B (2.2B active) IQ2_XXS 5.8 GiB — Doesn't fit
Mellum2-12B-A2.5B-Instruct-SFT 12.1B (2.2B active) IQ2_XXS 5.8 GiB — Doesn't fit
Mellum2-12B-A2.5B-Thinking-SFT 12.1B (2.2B active) IQ2_XXS 5.8 GiB — Doesn't fit
EuroLLM-9B-Instruct-2512 9.2B Q2_K 6.0 GiB — Doesn't fit
LFM2-8B-A1B 8.3B (1.6B active) Q4_0 6.0 GiB — Doesn't fit
LFM2.5-8B-A1B 8.5B (1.7B active) Q4_0 6.1 GiB — Doesn't fit
Qwen3.5-9B 9.0B Q3_K_M 6.1 GiB — Doesn't fit
Mellum2-12B-A2.5B-Instruct 12.1B (2.2B active) IQ2_M 6.5 GiB — Doesn't fit
Mellum2-12B-A2.5B-Thinking 12.1B (2.2B active) IQ2_M 6.5 GiB — Doesn't fit
NVIDIA-Nemotron-Nano-9B-v2 8.9B IQ2_M 6.5 GiB — Doesn't fit
FrogMini-14B-2510 14.8B IQ2_XXS 6.6 GiB — Doesn't fit
Nemotron-Terminal-14B 14.8B IQ2_XXS 6.6 GiB — Doesn't fit
Qwen3-Nemotron-14B-BRRM 14.8B IQ2_XXS 6.6 GiB — Doesn't fit
WebWorld-14B 14.8B IQ2_XXS 6.6 GiB — Doesn't fit
Mistral-Nemo-Instruct-2407 12.2B IQ2_M 6.7 GiB — Doesn't fit
granite-4.1-8b 8.8B Q3_K_M 6.7 GiB — Doesn't fit
MiniCPM-o-4_5 8.2B Q4_0 6.8 GiB — Doesn't fit
Bielik-Minitron-7B-v3.0-Instruct 7.5B Q4_K_M 6.9 GiB — Doesn't fit
ArmorOCR 8.2B Q4_K_M 7.1 GiB — Doesn't fit
Qwen3-8B 8.2B Q4_K_M 7.1 GiB — Doesn't fit
Ministral-3-8B-Instruct-2512 8.5B Q4_K_M 7.2 GiB — Doesn't fit
Ministral-3-8B-Reasoning-2512 8.5B Q4_K_M 7.2 GiB — Doesn't fit
Olmo-3.1-7B-RL-Zero-Code 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-Instruct-DPO 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-Instruct-SFT 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-RL-Zero-Code 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-RL-Zero-General 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-RL-Zero-IF 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-RL-Zero-Math 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-RL-Zero-Mix 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-Think-DPO 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Olmo-3-7B-Think-SFT 7.3B IQ2_XXS 7.5 GiB — Doesn't fit
Nemotron-Cascade-14B-Thinking 14.8B IQ2_M 7.5 GiB — Doesn't fit
NousCoder-14B 14.8B IQ2_M 7.5 GiB — Doesn't fit
Apriel-1.6-15b-Thinker 14.4B IQ2_M 7.6 GiB — Doesn't fit
gemma-2-9b-it 9.2B IQ2_M 7.7 GiB — Doesn't fit
JanusCoder-14B 14.8B Q2_K 8.0 GiB — Doesn't fit
ContextPilot-14B 14.8B IQ2_M 8.1 GiB — Doesn't fit
Qwen3-Coder-REAP-25B-A3B 24.9B (3.0B active) IQ2_XXS 8.1 GiB — Doesn't fit
Olmo-3.1-7B-RL-Zero-Math 7.3B Q2_K 8.2 GiB — Doesn't fit
Olmo-3-7B-Instruct 7.3B Q2_K 8.2 GiB — Doesn't fit
Olmo-3-7B-Think 7.3B Q2_K 8.2 GiB — Doesn't fit
gemma-3-12b-it 11.8B Q2_K 8.2 GiB — Doesn't fit
translategemma-12b-it 11.8B Q2_K 8.2 GiB — Doesn't fit
Trinity-Mini 26.1B (3.1B active) IQ2_XXS 8.2 GiB — Doesn't fit
phi-4 14.7B Q2_K 8.3 GiB — Doesn't fit
DeepSeek-R1-Distill-Qwen-14B 14.8B Q2_K 8.3 GiB — Doesn't fit
Qwen2.5-14B-Instruct 14.8B Q2_K 8.3 GiB — Doesn't fit
Trinity-Mini-Base-Pre-Anneal 26.1B (3.1B active) IQ2_XXS 8.4 GiB — Doesn't fit
Trinity-Mini-Base 26.1B (3.1B active) IQ2_XXS 8.7 GiB — Doesn't fit
gemma-4-12B-it 11.9B Q3_K_M 8.7 GiB — Doesn't fit
EuroLLM-22B-2512 22.6B IQ2_XXS 9.1 GiB — Doesn't fit
Mellum2.1-12B-A2.5B-Thinking 12.1B (2.2B active) Q4_K_M 9.4 GiB — Doesn't fit
Bielik-11B-v3.0-Instruct 11.2B Q4_K_M 9.4 GiB — Doesn't fit
Muse-Glimmer-30B 27.9B IQ2_XXS 10.2 GiB — Doesn't fit
GLM-4.7-Flash-REAP-23B-A3B 23.0B (3.6B active) Q2_K 10.2 GiB — Doesn't fit
Ministral-3-14B-Instruct-2512 13.5B Q4_K_M 10.3 GiB — Doesn't fit
Ministral-3-14B-Reasoning-2512 13.5B Q4_K_M 10.3 GiB — Doesn't fit
Holo4-27B 26.9B IQ2_XXS 10.5 GiB — Doesn't fit
EuroLLM-22B-Instruct-2512 22.6B IQ2_M 10.6 GiB — Doesn't fit
Qwen3.8-27B 26.9B IQ2_XXS 10.6 GiB — Doesn't fit
Qwen3.8-3.6-27B-blend 26.9B IQ2_XXS 10.6 GiB — Doesn't fit
Kimi-Linear-REAP-35B-A3B-Instruct 35.1B (3.1B active) IQ2_XXS 10.7 GiB — Doesn't fit
North-Mini-Code-1.0 30.5B (3.3B active) IQ2_XXS 10.7 GiB — Doesn't fit
Qwen3.5-35B-A3B-Base 34.7B (2.9B active) IQ2_XXS 10.9 GiB — Doesn't fit
Qwen3-14B 14.8B Q4_K_M 11.0 GiB — Doesn't fit
Laguna-XS-2.1 33.4B (2.8B active) IQ2_XXS 11.1 GiB — Doesn't fit
Ising-Calibration-1-35B-A3B 34.7B (2.9B active) IQ2_XXS 11.1 GiB — Doesn't fit
Devstral-Small-2-24B-Instruct-2512 23.6B Q2_K 11.1 GiB — Doesn't fit
Mistral-Small-3.2-24B-Instruct-2506 23.6B Q2_K 11.1 GiB — Doesn't fit
UI-Mate-27B 26.9B IQ2_XXS 11.2 GiB — Doesn't fit
Qwen3.6-35B-A3B 34.7B (2.9B active) IQ2_XXS 11.3 GiB — Doesn't fit
KAT-Coder-V2.5-Dev 34.7B (2.9B active) IQ2_XXS 11.3 GiB — Doesn't fit
Olmo-3.1-32B-Instruct-DPO 32.2B IQ2_XXS 11.8 GiB — Doesn't fit
Olmo-3-1125-32B 32.2B IQ2_XXS 11.8 GiB — Doesn't fit
Olmo-3-32B-Think-DPO 32.2B IQ2_XXS 11.8 GiB — Doesn't fit
Olmo-3-32B-Think-SFT 32.2B IQ2_XXS 11.8 GiB — Doesn't fit
Holo4-35B-A3B 34.7B (2.9B active) IQ2_XXS 12.0 GiB — Doesn't fit
Cosmos-Reason2-32B 32.8B IQ2_XXS 12.0 GiB — Doesn't fit
FrogBoss-32B-2510 32.8B IQ2_XXS 12.0 GiB — Doesn't fit
Nemotron-Terminal-32B 32.8B IQ2_XXS 12.0 GiB — Doesn't fit
SERA-32B 32.8B IQ2_XXS 12.0 GiB — Doesn't fit
WebWorld-32B 32.8B IQ2_XXS 12.0 GiB — Doesn't fit
gemma-4-26B-A4B-it 25.2B (3.8B active) IQ2_XXS 12.1 GiB — Doesn't fit
Fara1.5-27B 26.9B IQ2_M 12.5 GiB — Doesn't fit
gpt-oss-20b 20.9B (3.6B active) Q2_K 12.6 GiB — Doesn't fit
UI-Mate-democua-27B 26.9B Q2_K 12.7 GiB — Doesn't fit
GLM-4.7-Flash 29.9B (3.6B active) Q2_K 12.8 GiB — Doesn't fit
Hermes-4.3-36B 36.2B IQ2_XXS 12.9 GiB — Doesn't fit
gemma-4-26B-A4B 25.2B (3.8B active) Q2_K 13.0 GiB — Doesn't fit
Holo2-30B-A3B 30.5B (3.0B active) Q2_K 13.0 GiB — Doesn't fit
Qwen3-30B-A3B-Instruct-2507 30.5B (3.0B active) Q2_K 13.0 GiB — Doesn't fit
Qwen3-Coder-30B-A3B-Instruct 30.5B (3.0B active) Q2_K 13.0 GiB — Doesn't fit
Qwen3-VL-30B-A3B-Instruct 30.5B (3.0B active) Q2_K 13.0 GiB — Doesn't fit
UI-Venus-1.5-30B-A3B 30.5B (3.0B active) Q2_K 13.0 GiB — Doesn't fit
OptiMind-SFT 20.9B (3.6B active) IQ2_M 13.1 GiB — Doesn't fit
Kimi-Linear-48B-A3B-Instruct 49.1B (3.1B active) IQ2_XXS 13.3 GiB — Doesn't fit
AesCode-32B 32.8B IQ2_XXS 13.6 GiB — Doesn't fit
AI21-Jamba2-Mini 51.6B (11.8B active) IQ2_XXS 13.6 GiB — Doesn't fit
gemma-2-27b-it 27.2B IQ2_M 13.8 GiB — Doesn't fit
granite-4.1-30b 28.9B Q2_K 13.9 GiB — Doesn't fit
granite-4.2-30b 29.3B Q2_K 13.9 GiB — Doesn't fit
Kimi-Linear-48B-A3B-Base 49.1B (3.1B active) IQ2_XXS 14.2 GiB — Doesn't fit
gemma-3-27b-it 27.0B Q2_K 14.4 GiB — Doesn't fit
translategemma-27b-it 27.0B Q2_K 14.4 GiB — Doesn't fit
Holo-3.1-35B-A3B 34.7B (2.9B active) Q2_K 14.4 GiB — Doesn't fit
Holo3-35B-A3B 34.7B (2.9B active) Q2_K 14.4 GiB — Doesn't fit
LFM2-24B-A2B 23.8B (2.3B active) Q4_0 14.6 GiB — Doesn't fit
LFM2.5-24B-A2B 24.0B (2.5B active) Q4_0 14.7 GiB — Doesn't fit
Olmo-3.1-32B-Instruct 32.2B Q2_K 15.0 GiB — Doesn't fit
Olmo-3.1-32B-Think 32.2B Q2_K 15.0 GiB — Doesn't fit
Olmo-3-32B-Think 32.2B Q2_K 15.0 GiB — Doesn't fit
DeepSeek-R1-Distill-Qwen-32B 32.8B Q2_K 15.2 GiB — Doesn't fit
Qwen2.5-32B-Instruct 32.8B Q2_K 15.2 GiB — Doesn't fit
Qwen2.5-Coder-32B-Instruct 32.8B Q2_K 15.2 GiB — Doesn't fit
Qwen3-VL-32B-Instruct 32.8B Q2_K 15.3 GiB — Doesn't fit
Qwen3-VL-32B-Thinking 32.8B Q2_K 15.3 GiB — Doesn't fit
Qwen3.5-27B 26.9B Q3_K_M 15.3 GiB — Doesn't fit
Qwen3.6-27B 26.9B Q3_K_M 15.4 GiB — Doesn't fit
gemma-4-12B 11.9B Q8_0 15.6 GiB — Doesn't fit
Ising-Calibration-1.5-31B-BF16 30.7B IQ2_XXS 16.5 GiB — Doesn't fit
Qwen3.5-35B-A3B 34.7B (2.9B active) Q3_K_M 17.6 GiB — Doesn't fit
gemma-4-31B 30.7B Q2_K 17.6 GiB — Doesn't fit
Holotron4-30B-A3B 31.6B (3.2B active) IQ2_M 18.9 GiB — Doesn't fit
NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16 31.6B (3.2B active) IQ2_M 18.9 GiB — Doesn't fit
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 31.6B (3.2B active) Q2_K 18.9 GiB — Doesn't fit
Nemotron-Cascade-2-30B-A3B 31.6B (3.2B active) IQ2_M 19.1 GiB — Doesn't fit
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 31.6B (3.2B active) IQ2_M 19.1 GiB — Doesn't fit
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 31.6B (3.2B active) IQ4_XS 19.1 GiB — Doesn't fit
MiniCPM-V-4.7-35B-A3B 34.7B (2.9B active) IQ4_XS 20.0 GiB — Doesn't fit
Qwen3-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB — Doesn't fit
gemma-4-31B-it 30.7B Q3_K_M 20.3 GiB — Doesn't fit
EXAONE-4.5-33B 32.5B IQ4_XS 20.4 GiB — Doesn't fit
Llama-3.1-70B-Instruct 70.6B IQ2_XXS 22.3 GiB — Doesn't fit
Qwen3-Coder-Next-Base 79.7B (3.6B active) IQ2_XXS 22.3 GiB — Doesn't fit
Qwen3-32B 32.8B Q4_K_M 22.4 GiB — Doesn't fit
QwQ-32B 32.8B Q4_K_M 22.5 GiB — Doesn't fit
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 31.6B (3.2B active) Q4_K_M 23.3 GiB — Doesn't fit
KAT-Dev-72B-Exp 72.7B IQ2_XXS 28.5 GiB — Doesn't fit
Solar-Open-100B 103B (11.2B active) IQ2_XXS 29.4 GiB — Doesn't fit
DeepSeek-R1-Distill-Llama-70B 70.6B Q2_K 29.4 GiB — Doesn't fit
Llama-3.3-70B-Instruct 70.6B Q2_K 29.4 GiB — Doesn't fit
Qwen3-Next-80B-A3B-Instruct 79.7B (3.6B active) Q2_K 30.3 GiB — Doesn't fit
Qwen2.5-72B-Instruct 73.0B Q2_K 30.3 GiB — Doesn't fit
Qwen3-Coder-Next 79.7B (3.6B active) Q2_K 30.4 GiB — Doesn't fit
GLM-4.5-Air-REAP-82B-A12B 81.9B (12.8B active) IQ2_XXS 31.1 GiB — Doesn't fit
Step-3.5-Flash-REAP-121B-A11B 121B (11.4B active) IQ2_XXS 32.9 GiB — Doesn't fit
Mistral-Small-4-119B-2603 119B (6.1B active) IQ2_XXS 34.3 GiB — Doesn't fit
Qwen3.5-122B-A10B 122B (9.0B active) IQ2_XXS 35.0 GiB — Doesn't fit
Qwen-AgentWorld-35B-A3B 34.7B (2.9B active) Q8_0 37.6 GiB Does not fit even on 8 cards. Doesn't fit
MiniMax-M2.5-REAP-139B-A10B 139B (10.4B active) IQ2_XXS 39.2 GiB Does not fit even on 8 cards. Doesn't fit
INTELLECT-3 107B (12.8B active) IQ2_XXS 39.6 GiB Does not fit even on 8 cards. Doesn't fit
Step-3.5-Flash-REAP-149B-A11B 149B (11.4B active) IQ2_XXS 40.1 GiB Does not fit even on 8 cards. Doesn't fit
Llama-4-Scout-17B-16E-Instruct 108B (16.1B active) Q2_K 41.5 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.5-Air 107B (12.8B active) Q2_K 45.6 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.6V 107B (12.8B active) Q2_K 45.6 GiB Does not fit even on 8 cards. Doesn't fit
Step-3.5-Flash 197B (11.5B active) IQ2_XXS 48.9 GiB Does not fit even on 8 cards. Doesn't fit
Devstral-2-123B-Instruct-2512 125B Q2_K 49.3 GiB Does not fit even on 8 cards. Doesn't fit
Mistral-Medium-3.5-128B 125B Q2_K 49.3 GiB Does not fit even on 8 cards. Doesn't fit
NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 121B (12.2B active) IQ2_XXS 49.8 GiB Does not fit even on 8 cards. Doesn't fit
NVIDIA-Nemotron-3-Super-120B-A12B-BF16 121B (12.2B active) IQ2_XXS 51.0 GiB Does not fit even on 8 cards. Doesn't fit
gpt-oss-120b 117B (5.1B active) Q2_K 62.8 GiB Does not fit even on 8 cards. Doesn't fit
MiniMax-M2.7 229B (10.4B active) IQ2_XXS 62.9 GiB Does not fit even on 8 cards. Doesn't fit
Baichuan-M3-235B 235B (21.6B active) IQ2_XXS 63.2 GiB Does not fit even on 8 cards. Doesn't fit
Holo2-235B-A22B 235B (21.6B active) IQ2_XXS 63.2 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3-Nemotron-235B-A22B-GenRM 235B (21.6B active) IQ2_XXS 63.2 GiB Does not fit even on 8 cards. Doesn't fit
command-a-plus-05-2026-bf16 218B (25.0B active) IQ2_XXS 63.6 GiB Does not fit even on 8 cards. Doesn't fit
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 121B (12.2B active) Q4_0 71.8 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.7-REAP-268B-A32B 269B (32.8B active) IQ2_XXS 73.0 GiB Does not fit even on 8 cards. Doesn't fit
Step-3.7-Flash 197B (11.5B active) IQ3_XXS 76.1 GiB Does not fit even on 8 cards. Doesn't fit
Hy3 295B (20.2B active) IQ2_XXS 82.2 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.5 309B (14.8B active) IQ2_XXS 82.4 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.7-REAP-218B-A32B 218B (32.8B active) Q2_K 82.9 GiB Does not fit even on 8 cards. Doesn't fit
MiniMax-M2 229B (10.4B active) Q2_K 84.9 GiB Does not fit even on 8 cards. Doesn't fit
MiniMax-M2.1 229B (10.4B active) Q2_K 84.9 GiB Does not fit even on 8 cards. Doesn't fit
MiniMax-M2.5 229B (10.4B active) Q2_K 84.9 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3-235B-A22B-Instruct-2507 235B (21.6B active) Q2_K 86.7 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3-VL-235B-A22B-Instruct 235B (21.6B active) Q2_K 86.7 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.3-Flash-BF16 313B (16.7B active) IQ2_XXS 92.0 GiB Does not fit even on 8 cards. Doesn't fit
Laguna-S-2.1 118B (8.1B active) Q4_K_M 95.9 GiB Does not fit even on 8 cards. Doesn't fit
Trinity-Large-Base 399B (12.8B active) IQ2_XXS 96.4 GiB Does not fit even on 8 cards. Doesn't fit
Trinity-Large-TrueBase 399B (12.8B active) IQ2_XXS 96.4 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.6-REAP-268B-A32B 269B (32.8B active) Q2_K 100.9 GiB Does not fit even on 8 cards. Doesn't fit
Trinity-Large-Thinking 399B (12.8B active) IQ2_XXS 107.1 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2-Flash 309B (14.8B active) Q2_K 111.6 GiB Does not fit even on 8 cards. Doesn't fit
Intern-S2-397B 396B (16.3B active) IQ2_XXS 114.3 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.6-Flash-MOPD 309B (14.8B active) Q2_K 124.9 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.6-Flash-RL 309B (14.8B active) Q2_K 124.9 GiB Does not fit even on 8 cards. Doesn't fit
K-EXAONE-236B-A23B 237B (22.7B active) IQ4_XS 126.3 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.5 353B (32.9B active) Q2_K 130.7 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.7 353B (32.9B active) Q2_K 130.7 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3-Coder-REAP-363B-A35B 363B (34.5B active) Q2_K 132.7 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3-235B-A22B 235B (21.6B active) Q4_K_M 141.9 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3-Coder-480B-A35B-Instruct 480B (34.5B active) Q2_K 174.3 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3.5-397B-A17B 396B (16.3B active) Q3_K_M 175.6 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.1 744B (40.8B active) IQ2_XXS 197.6 GiB Does not fit even on 8 cards. Doesn't fit
DeepSeek-V3.2 671B (36.6B active) Q2_K 242.1 GiB Does not fit even on 8 cards. Doesn't fit
cogito-671b-v2.1 671B (36.6B active) Q2_K 242.4 GiB Does not fit even on 8 cards. Doesn't fit
DeepSeek-V3.1 671B (36.6B active) Q2_K 242.4 GiB Does not fit even on 8 cards. Doesn't fit
Mistral-Large-3-675B-Instruct-2512 673B (39.0B active) Q2_K 243.8 GiB Does not fit even on 8 cards. Doesn't fit
DeepSeek-V3 671B (36.6B active) Q2_K 257.8 GiB Does not fit even on 8 cards. Doesn't fit
Kimi-K2.6 1.03T (31.7B active) IQ2_XXS 267.6 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5 744B (40.8B active) Q2_K 268.9 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.5-Pro 1.02T (41.0B active) IQ2_XXS 270.4 GiB Does not fit even on 8 cards. Doesn't fit
DeepSeek-R1 671B (36.6B active) Q2_K 280.3 GiB Does not fit even on 8 cards. Doesn't fit
Muse-Spark-Open-816B-A42B 820B (44.4B active) Q2_K 301.0 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.3-Flash 313B (16.7B active) Q8_0 327.9 GiB Does not fit even on 8 cards. Doesn't fit
Ling-1T 1.00T (49.8B active) Q2_K 360.6 GiB Does not fit even on 8 cards. Doesn't fit
Kimi-K2-Instruct 1.03T (31.7B active) Q2_K 367.4 GiB Does not fit even on 8 cards. Doesn't fit
Kimi-K2.5 1.03T (31.7B active) Q2_K 368.0 GiB Does not fit even on 8 cards. Doesn't fit
Kimi-K2-Thinking 1.03T (31.7B active) Q2_K 368.3 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.6-Pro-MOPD 1.02T (41.0B active) Q2_K 411.6 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.6-Pro-RL 1.02T (41.0B active) Q2_K 411.6 GiB Does not fit even on 8 cards. Doesn't fit
Beam-1.0-501B-A23B 501B (22.7B active) Q8_0 523.6 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.2 744B (40.8B active) Q8_0 776.4 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.3 744B (40.8B active) Q8_0 776.4 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3.8-2.4T-A95B 2.42T (93.3B active) Q8_0 2,524.1 GiB Does not fit even on 8 cards. Doesn't fit

Models without a verdict on this GPU

Context 8,192 tokens. No verdict is given for these rows (see the last columns); the requirement shown is for the lowest quantization.
Model Parameters Smallest quantization Available memory needed for “Fits” Why no verdict Result
LFM2.5-Encoder-350M-Diffusion 354M IQ2_XXS 1.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-230M 230M Q4_0 1.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
granite-4.0-h-350m 340M Q2_K 1.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-350M 354M Q4_0 1.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-VL-450M 354M Q4_0 1.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-VL-450M-Extract 354M Q4_0 1.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
granite-4.0-350m 352M Q2_K 1.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiniCPM5-1B 1.1B IQ2_XXS 1.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiniCPM5-1B-Base 1.1B IQ2_XXS 1.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiniCPM5-1B-SFT 1.1B IQ2_XXS 1.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
functiongemma-270m-it 268M IQ4_XS 1.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Apertus-v1.1-1.5B 1.5B Q2_K 2.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Apertus-v1.1-1.5B-Instruct 1.5B Q2_K 2.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Holo-3.1-0.8B 1.0B IQ2_XXS 2.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3.5-0.8B-Base 752M IQ2_XXS 2.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-1.2B-Base 1.2B Q4_0 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-1.2B-Instruct 1.2B Q4_0 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-1.2B-JP 1.2B Q4_0 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-1.2B-JP-202606 1.2B Q4_0 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-1.2B-Thinking 1.2B Q4_0 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-VL-1.6B 1.2B Q4_0 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-VL-1.6B-Extract 1.2B Q4_0 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Llama-3.2-1B-Instruct 1.2B Q2_K 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3.5-0.8B 752M Q3_K_M 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
granite-4.0-h-1b 1.5B Q2_K 2.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiniCPM-V-4.6 752M Q4_0 2.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiniCPM-V-4.6-Thinking 752M Q4_0 2.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiniCPM-V-4.7-1B 1.0B Q4_0 2.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Youtu-LLM-2B 2.0B IQ2_XXS 2.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Youtu-LLM-2B-Base 2.0B IQ2_XXS 2.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
EuroMoE-2.6B-A0.6B-Instruct-2512 2.6B (498M active) IQ2_XXS 2.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-2.6B-Base 2.7B IQ2_XXS 2.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
gemma-3-1b-it 1.0B Q2_K 2.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiniCPM5-2B-Base 2.5B IQ2_XXS 2.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
HunyuanOCR 539M Q2_K 2.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
AI21-Jamba-Reasoning-3B 3.2B IQ2_M 2.4 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
AI21-Jamba2-3B 3.2B IQ2_M 2.4 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2-2.6B-Longevity 2.6B Q2_K 2.4 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3.5-2B-Base 1.9B IQ2_XXS 2.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiniCPM5-2B 2.5B IQ2_M 2.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
BitCPM-CANN-3B-unquantized 3.6B IQ2_XXS 2.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-0.6B 752M Q4_0 2.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
granite-4.0-1b 1.6B Q2_K 2.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
gemma-4-E2B 4.6B Q2_K 2.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Apertus-v1.1-4B 3.8B IQ2_XXS 2.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3.5-2B 1.9B Q3_K_M 2.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
SmolLM3-3B-GSM8K-SFT 3.1B IQ2_XXS 2.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
gemma-4-E2B-it 4.6B Q3_K_M 2.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
HiPO-1.7B 2.0B IQ2_XXS 2.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen2.5-3B-Instruct 3.4B Q2_K 2.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2-2.6B-Exp 2.7B Q4_0 2.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2-2.6B-Transcript 2.6B Q4_0 2.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2-VL-3B 2.6B Q4_0 2.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
granite-guardian-4.0-3b-toxicity-ja 3.4B IQ2_XXS 2.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-2.6B 2.7B Q4_0 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
LFM2.5-VL-3B 2.7B Q4_0 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
CapRL-Qwen3VL-2B 2.0B Q2_K 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-1.7B 1.7B Q2_K 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-VL-2B-Instruct 1.7B Q2_K 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-VL-2B-Thinking 1.7B Q2_K 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
SingGuard-2b 1.7B Q2_K 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
UI-Venus-1.5-2B 2.0B Q2_K 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
d1-3B 2.7B Q4_K_M 3.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
SmolLM3-3B 3.1B Q2_K 3.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Trinity-Nano-Base-Pre-Anneal 6.1B (819M active) IQ2_XXS 3.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
granite-4.1-3b 3.4B Q2_K 3.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
granite-4.2-3b 3.7B Q2_K 3.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
kanana-2-3b-base 3.2B IQ2_XXS 3.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
ZwZ-2B 2.0B Q4_K_M 3.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Trinity-Nano-Base 6.1B (819M active) IQ2_XXS 3.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
FrogNano-4B-2609 4.2B IQ2_M 3.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
UserRepGen-4B 4.2B IQ2_M 3.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Llama-3.2-3B-Instruct 3.2B Q2_K 3.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Nemotron-3-Content-Safety 3.9B IQ2_XXS 3.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Youtu-VL-4B-Instruct 4.9B IQ2_XXS 3.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
kanana-2-3b-instruct 3.5B Q2_K 3.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
AgentCPM-Explore 4.4B IQ2_XXS 3.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
ZwZ-4B 4.4B IQ2_XXS 3.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Fara1.5-4B 4.2B IQ2_M 3.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
ContextPilot-E4B 7.5B Q2_K 3.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
gemma-4-E4B 7.5B Q2_K 3.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
HARC-Qwen2.5-7B-Instruct 7.6B IQ2_XXS 3.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Spatial-SSRL-7B 7.6B IQ2_XXS 3.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
X-Reasoner-7B 7.6B IQ2_XXS 3.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
ZwZ-7B 7.6B IQ2_XXS 3.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Trinity-Nano-Preview 6.1B (819M active) IQ2_M 3.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Holo-3.1-4B 4.8B Q2_K 3.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3.5-4B-Base 4.2B Q2_K 3.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Riva-Translate-4B-Instruct-v1.1 4.2B IQ2_XXS 3.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
NVIDIA-Nemotron-3-Nano-4B-BF16 4.0B Q3_K_M 3.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
gemma-3-4b-it 3.9B Q2_K 3.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
medgemma-1.5-4b-it 3.9B Q2_K 3.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
translategemma-4b-it 3.9B Q2_K 3.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
GELab-Zero-4B-preview 4.0B IQ2_M 4.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
granite-vision-4.1-4b 3.4B Q4_K_M 4.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Phi-4-mini-instruct 3.8B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
tiny-aya-earth 3.3B Q4_0 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
tiny-aya-fire 3.3B Q4_0 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
tiny-aya-global 3.3B Q4_0 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
tiny-aya-water 3.3B Q4_0 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
CapRL-Qwen3VL-4B 4.4B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Holo2-4B 4.4B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-qwen3-4b-baseline 4.4B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-qwen3-4b-intent-explicit 4.4B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-qwen3-4b-intent-implicit 4.4B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-qwen3-4b-multiview 4.4B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-4B-Instruct-2507 4.0B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-VL-4B-Instruct 4.0B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-VL-4B-Thinking 4.0B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Spatial-SSRL-Qwen3VL-4B 4.4B Q2_K 4.1 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
gemma-4-E4B-it 7.5B Q3_K_M 4.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3.5-4B 4.2B Q3_K_M 4.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
AprielGuard 7.9B IQ2_XXS 4.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Ministral-3-3B-Instruct-2512 3.4B Q4_K_M 4.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Ministral-3-3B-Reasoning-2512 3.4B Q4_K_M 4.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Mistral-7B-Instruct-v0.2 7.2B IQ2_XXS 4.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Fara-7B 7.6B IQ2_M 4.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
JanusCoderV-7B 7.6B IQ2_M 4.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
olmOCR-2-7B-1025 7.6B IQ2_M 4.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
HARC-Llama-3.1-8B-Instruct 8.0B IQ2_XXS 4.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
DeepSeek-R1-Distill-Qwen-7B 7.6B Q2_K 4.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen2.5-7B-Instruct 7.6B Q2_K 4.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen2.5-Coder-7B-Instruct 7.6B Q2_K 4.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen2.5-VL-7B-Instruct 7.6B Q2_K 4.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen2.5-VL-7B-Surg-CholecT50 7.6B Q2_K 4.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiMo-Embodied-7B 7.6B IQ2_XXS 4.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
AstaBrief_8B 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
ContextPilot-8B 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Cosmos-Reason2-8B 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Holo2-8B 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Nemotron-Terminal-8B 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-Nemotron-8B-BRRM 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
RLVR-8B-0926 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Step3-VL-10B-Base 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
UI-Venus-1.5-8B 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
ZwZ-8B 8.2B IQ2_XXS 4.7 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
AutoGLM-Phone-9B-Multilingual 9.4B IQ2_XXS 4.8 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-4B 4.0B Q4_K_M 4.9 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MiMo-V2.6-Distill-Qwen-9B 9.0B IQ2_M 5.0 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Nemotron-Cascade-8B 8.2B IQ2_M 5.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Nemotron-Cascade-8B-Thinking 8.2B IQ2_M 5.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Nemotron-Orchestrator-8B 8.2B IQ2_M 5.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Fara1.5-9B 9.0B IQ2_M 5.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
UI-Mate-9B 9.0B IQ2_M 5.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
UI-Venus-2-9B 9.0B IQ2_M 5.2 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
DeepSeek-R1-Distill-Llama-8B 8.0B Q2_K 5.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Llama-3.1-8B-Instruct 8.0B Q2_K 5.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-llama3-8b-baseline 8.0B Q2_K 5.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-llama3-8b-intent-explicit 8.0B Q2_K 5.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-llama3-8b-intent-implicit 8.0B Q2_K 5.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-llama3-8b-multiview 8.0B Q2_K 5.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
AesCode-8B 8.2B IQ2_M 5.3 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
AutoGLM-Phone-9B 9.4B Q2_K 5.4 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
GLM-4.6V-Flash 9.4B Q2_K 5.4 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Holo-3.1-9B 9.0B Q2_K 5.4 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3.5-9B-Base 9.0B Q2_K 5.4 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
DeepSeek-R1-0528-Qwen3-8B 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-qwen3-8b-baseline 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-qwen3-8b-intent-explicit 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-qwen3-8b-intent-implicit 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
intent-aware-lfqa-qwen3-8b-multiview 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
JanusCoder-8B 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
MathForm-8B 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-VL-8B-Instruct 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
Qwen3-VL-8B-Thinking 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
WebWorld-8B 8.2B Q2_K 5.5 GiB Unknown: too little memory left after the reserve to judge reliably Unknown
rnj-1-instruct 8.3B Q2_K 5.6 GiB Unknown: too little memory left after the reserve to judge reliably Unknown

The speed ceiling is memory bandwidth divided by the bytes read per generated token. It is a theoretical upper bound; public llama.cpp benchmarks typically reach about half to four-fifths of it, and small models and mixture-of-experts models often less. Public benchmarks

Other devices with 4 GB