DeskGPU
English

AMD Radeon RX 7800 XT: 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

AMD Radeon RX 7800 XT has 16 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)
16 GB
Memory type
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
Memory bus width
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
Memory bandwidth
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
Board power (TDP)
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
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, ROCm back end on Linux (AMD 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.

Memory counted as available for “Fits” (C_low): 14.75 GiB per card = 16 GiB nominal − 16 MiB (nominal minus the total that llama.cpp reported for this GPU in public logs) − 1,216 MiB (the largest start-up and runtime use seen in this profile’s public logs), rounded down to a multiple of 64 MiB.

These results apply to the configuration seen in public logs, where llama.cpp reported 16,368 MiB of total memory for this GPU. Settings that reduce usable memory (for example ECC, where the card supports it) are not covered.

Memory used for “Doesn’t fit” (C_high): the full 16 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

No speed ceiling: the bandwidth could not be confirmed by two open sources.

Context 8,192 tokens (or the model’s maximum if shorter). The last columns show the longest context at that quantization and the bandwidth-based speed ceiling.
Model Parameters Highest quantization that fits Available memory needed for “Fits” Longest context Speed ceiling Result
AI21-Jamba2-Mini 51.6B (11.8B active) IQ2_XXS 13.6 GiB 70,144 — Fits
Kimi-Linear-48B-A3B-Base 49.1B (3.1B active) IQ2_XXS 14.2 GiB 59,904 — Fits
Kimi-Linear-48B-A3B-Instruct 49.1B (3.1B active) IQ2_XXS 13.3 GiB 149,504 — Fits
Hermes-4.3-36B 36.2B IQ2_XXS 12.9 GiB 15,360 — Fits
Kimi-Linear-REAP-35B-A3B-Instruct 35.1B (3.1B active) Q2_K 14.2 GiB 68,352 — Fits
Holo-3.1-35B-A3B 34.7B (2.9B active) Q2_K 14.4 GiB 21,760 — Fits
Holo3-35B-A3B 34.7B (2.9B active) Q2_K 14.4 GiB 21,760 — Fits
Holo4-35B-A3B 34.7B (2.9B active) IQ2_M 14.4 GiB 25,344 — Fits
Ising-Calibration-1-35B-A3B 34.7B (2.9B active) Q2_K 14.4 GiB 21,760 — Fits
KAT-Coder-V2.5-Dev 34.7B (2.9B active) Q2_K 14.1 GiB 36,096 — Fits
Qwen3.5-35B-A3B-Base 34.7B (2.9B active) Q2_K 14.3 GiB 26,880 — Fits
Qwen3.6-35B-A3B 34.7B (2.9B active) Q2_K 14.1 GiB 36,352 — Fits
Laguna-XS-2.1 33.4B (2.8B active) Q2_K 13.8 GiB 31,232 — Fits
AesCode-32B 32.8B IQ2_XXS 13.6 GiB 12,544 — Fits
Cosmos-Reason2-32B 32.8B IQ2_M 14.2 GiB 9,984 — Fits
FrogBoss-32B-2510 32.8B IQ2_M 14.2 GiB 9,984 — Fits
Nemotron-Terminal-32B 32.8B IQ2_M 14.2 GiB 9,984 — Fits
SERA-32B 32.8B IQ2_M 14.2 GiB 9,984 — Fits
WebWorld-32B 32.8B IQ2_M 14.2 GiB 9,984 — Fits
Olmo-3.1-32B-Instruct-DPO 32.2B IQ2_M 13.9 GiB 11,264 — Fits
Olmo-3-1125-32B 32.2B IQ2_M 13.9 GiB 11,264 — Fits
Olmo-3-32B-Think-DPO 32.2B IQ2_M 13.9 GiB 11,264 — Fits
Olmo-3-32B-Think-SFT 32.2B IQ2_M 13.9 GiB 11,264 — Fits
Holo2-30B-A3B 30.5B (3.0B active) Q2_K 13.0 GiB 25,344 — Fits
Qwen3-30B-A3B-Instruct-2507 30.5B (3.0B active) Q2_K 13.0 GiB 25,344 — Fits
Qwen3-Coder-30B-A3B-Instruct 30.5B (3.0B active) Q2_K 13.0 GiB 25,344 — Fits
Qwen3-VL-30B-A3B-Instruct 30.5B (3.0B active) Q2_K 13.0 GiB 25,344 — Fits
UI-Venus-1.5-30B-A3B 30.5B (3.0B active) Q2_K 13.0 GiB 25,344 — Fits
North-Mini-Code-1.0 30.5B (3.3B active) Q2_K 13.2 GiB 39,168 — Fits
GLM-4.7-Flash 29.9B (3.6B active) Q2_K 12.8 GiB 44,032 — Fits
granite-4.2-30b 29.3B Q2_K 13.9 GiB 11,264 — Fits
granite-4.1-30b 28.9B Q2_K 13.9 GiB 11,264 — Fits
Muse-Glimmer-30B 27.9B IQ3_XXS 12.6 GiB 131,072 — Fits
gemma-2-27b-it 27.2B IQ2_M 13.8 GiB 8,192 — Fits
gemma-3-27b-it 27.0B Q2_K 14.4 GiB 12,032 — Fits
translategemma-27b-it 27.0B Q2_K 14.4 GiB 12,032 — Fits
Fara1.5-27B 26.9B IQ3_XXS 14.3 GiB 15,616 — Fits
Holo4-27B 26.9B IQ3_XXS 13.1 GiB 33,280 — Fits
Qwen3.8-27B 26.9B IQ3_XXS 13.8 GiB 22,528 — Fits
Qwen3.8-3.6-27B-blend 26.9B IQ3_XXS 13.8 GiB 22,528 — Fits
UI-Mate-27B 26.9B IQ3_XXS 14.3 GiB 15,616 — Fits
UI-Mate-democua-27B 26.9B Q2_K 12.7 GiB 38,400 — Fits
Trinity-Mini 26.1B (3.1B active) Q3_K_M 13.6 GiB 67,584 — Fits
Trinity-Mini-Base 26.1B (3.1B active) Q3_K_M 14.1 GiB 43,776 — Fits
Trinity-Mini-Base-Pre-Anneal 26.1B (3.1B active) Q3_K_M 13.8 GiB 4,096 — Fits
gemma-4-26B-A4B 25.2B (3.8B active) Q2_K 13.0 GiB 87,296 — Fits
gemma-4-26B-A4B-it 25.2B (3.8B active) IQ3_XXS 14.5 GiB 17,152 — Fits
Qwen3-Coder-REAP-25B-A3B 24.9B (3.0B active) Q3_K_M 13.3 GiB 23,296 — Fits
LFM2.5-24B-A2B 24.0B (2.5B active) Q4_0 14.7 GiB 8,192 — Fits
LFM2-24B-A2B 23.8B (2.3B active) Q4_0 14.6 GiB 12,800 — Fits
Devstral-Small-2-24B-Instruct-2512 23.6B IQ4_XS 14.7 GiB 8,192 — Fits
Mistral-Small-3.2-24B-Instruct-2506 23.6B IQ4_XS 14.7 GiB 8,192 — Fits
GLM-4.7-Flash-REAP-23B-A3B 23.0B (3.6B active) Q4_0 14.6 GiB 10,752 — Fits
EuroLLM-22B-2512 22.6B IQ4_XS 14.7 GiB 8,192 — Fits
EuroLLM-22B-Instruct-2512 22.6B IQ4_XS 14.7 GiB 8,192 — Fits
gpt-oss-20b 20.9B (3.6B active) Q8_0 12.9 GiB 78,848 — Fits
OptiMind-SFT 20.9B (3.6B active) Q4_0 13.2 GiB 66,560 — Fits
DeepSeek-R1-Distill-Qwen-14B 14.8B Q6_K 14.2 GiB 11,008 — Fits
Qwen2.5-14B-Instruct 14.8B Q6_K 14.2 GiB 11,008 — Fits
ContextPilot-14B 14.8B Q6_K 14.3 GiB 10,496 — Fits
FrogMini-14B-2510 14.8B Q6_K 13.9 GiB 13,312 — Fits
JanusCoder-14B 14.8B Q6_K 13.9 GiB 13,312 — Fits
Nemotron-Cascade-14B-Thinking 14.8B Q6_K 13.9 GiB 13,312 — Fits
Nemotron-Terminal-14B 14.8B Q6_K 13.9 GiB 13,312 — Fits
NousCoder-14B 14.8B Q6_K 13.9 GiB 13,312 — Fits
Qwen3-14B 14.8B Q6_K 13.9 GiB 13,312 — Fits
Qwen3-Nemotron-14B-BRRM 14.8B Q6_K 13.9 GiB 13,312 — Fits
WebWorld-14B 14.8B Q6_K 13.9 GiB 13,312 — Fits
phi-4 14.7B Q6_K 14.3 GiB 10,240 — Fits
Apriel-1.6-15b-Thinker 14.4B Q6_K 13.9 GiB 12,288 — Fits
Ministral-3-14B-Instruct-2512 13.5B Q5_K_M 11.6 GiB 27,648 — Fits
Ministral-3-14B-Reasoning-2512 13.5B Q5_K_M 11.6 GiB 27,648 — Fits
Mistral-Nemo-Instruct-2407 12.2B Q8_0 14.7 GiB 8,704 — Fits
Mellum2.1-12B-A2.5B-Thinking 12.1B (2.2B active) Q8_0 14.0 GiB 52,992 — Fits
Mellum2-12B-A2.5B-Base 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 — Fits
Mellum2-12B-A2.5B-Instruct 12.1B (2.2B active) Q8_0 14.0 GiB 52,992 — Fits
Mellum2-12B-A2.5B-Instruct-SFT 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 — Fits
Mellum2-12B-A2.5B-Thinking 12.1B (2.2B active) Q8_0 14.0 GiB 52,992 — Fits
Mellum2-12B-A2.5B-Thinking-SFT 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 — Fits
gemma-4-12B-it 11.9B Q6_K 12.7 GiB 119,296 — Fits
gemma-3-12b-it 11.8B Q6_K 13.0 GiB 34,048 — Fits
translategemma-12b-it 11.8B Q6_K 13.0 GiB 34,048 — Fits
Bielik-11B-v3.0-Instruct 11.2B Q8_0 14.4 GiB 9,728 — Fits
AutoGLM-Phone-9B 9.4B Q8_0 10.8 GiB 65,536 — Fits
AutoGLM-Phone-9B-Multilingual 9.4B Q6_K 9.2 GiB 65,536 — Fits
GLM-4.6V-Flash 9.4B Q8_0 10.8 GiB 101,888 — Fits
gemma-2-9b-it 9.2B Q6_K 12.0 GiB 8,192 — Fits
EuroLLM-9B-Instruct-2512 9.2B Q8_0 11.6 GiB 26,112 — Fits
Fara1.5-9B 9.0B Q8_0 10.3 GiB 139,264 — Fits
Holo-3.1-9B 9.0B Q8_0 10.3 GiB 139,776 — Fits
MiMo-V2.6-Distill-Qwen-9B 9.0B Q8_0 10.3 GiB 139,264 — Fits
Qwen3.5-9B 9.0B Q8_0 10.3 GiB 139,776 — Fits
Qwen3.5-9B-Base 9.0B Q8_0 10.3 GiB 139,776 — Fits
UI-Mate-9B 9.0B Q8_0 10.3 GiB 139,264 — Fits
UI-Venus-2-9B 9.0B Q8_0 10.3 GiB 139,264 — Fits
NVIDIA-Nemotron-Nano-9B-v2 8.9B Q8_0 10.6 GiB 131,072 — Fits
granite-4.1-8b 8.8B Q8_0 11.3 GiB 29,184 — Fits
granite-4.2-8b 8.8B Q8_0 11.3 GiB 29,184 — Fits
Ministral-3-8B-Instruct-2512 8.5B Q8_0 10.7 GiB 37,376 — Fits
Ministral-3-8B-Reasoning-2512 8.5B Q8_0 10.7 GiB 37,376 — Fits
LFM2.5-8B-A1B 8.5B (1.7B active) Q8_0 10.2 GiB 128,000 — Fits
granite-guardian-4.1-8b 8.4B Q8_0 11.3 GiB 29,184 — Fits
LFM2-8B-A1B 8.3B (1.6B active) Q8_0 10.1 GiB 128,000 — Fits
rnj-1-instruct 8.3B Q8_0 11.0 GiB 32,768 — Fits
AesCode-8B 8.2B Q8_0 10.4 GiB 37,888 — Fits
ArmorOCR 8.2B Q8_0 10.4 GiB 37,888 — Fits
AstaBrief_8B 8.2B Q6_K 8.6 GiB 40,960 — Fits
ContextPilot-8B 8.2B Q6_K 8.6 GiB 40,960 — Fits
Cosmos-Reason2-8B 8.2B Q6_K 8.6 GiB 50,176 — Fits
DeepSeek-R1-0528-Qwen3-8B 8.2B Q8_0 10.4 GiB 37,888 — Fits
Holo2-8B 8.2B Q6_K 8.6 GiB 50,176 — Fits
intent-aware-lfqa-qwen3-8b-baseline 8.2B Q8_0 10.4 GiB 37,888 — Fits
intent-aware-lfqa-qwen3-8b-intent-explicit 8.2B Q8_0 10.4 GiB 37,888 — Fits
intent-aware-lfqa-qwen3-8b-intent-implicit 8.2B Q8_0 10.4 GiB 37,888 — Fits
intent-aware-lfqa-qwen3-8b-multiview 8.2B Q8_0 10.4 GiB 37,888 — Fits
JanusCoder-8B 8.2B Q8_0 10.4 GiB 32,768 — Fits
MathForm-8B 8.2B Q8_0 10.4 GiB 37,888 — Fits
Nemotron-Cascade-8B 8.2B Q8_0 10.4 GiB 32,768 — Fits
Nemotron-Cascade-8B-Thinking 8.2B Q8_0 10.4 GiB 32,768 — Fits
Nemotron-Orchestrator-8B 8.2B Q8_0 10.4 GiB 37,888 — Fits
Nemotron-Terminal-8B 8.2B Q6_K 8.6 GiB 40,960 — Fits
Qwen3-8B 8.2B Q8_0 10.4 GiB 37,888 — Fits
Qwen3-Nemotron-8B-BRRM 8.2B Q6_K 8.6 GiB 40,960 — Fits
Qwen3-VL-8B-Instruct 8.2B Q8_0 10.4 GiB 37,888 — Fits
Qwen3-VL-8B-Thinking 8.2B Q8_0 10.4 GiB 37,888 — Fits
RLVR-8B-0926 8.2B Q6_K 8.6 GiB 50,176 — Fits
Step3-VL-10B-Base 8.2B Q6_K 8.6 GiB 40,960 — Fits
UI-Venus-1.5-8B 8.2B Q6_K 8.6 GiB 50,176 — Fits
WebWorld-8B 8.2B Q8_0 10.4 GiB 37,888 — Fits
ZwZ-8B 8.2B Q6_K 8.6 GiB 50,176 — Fits
MiniCPM-o-4_5 8.2B Q8_0 10.4 GiB 37,888 — Fits
granite-3.3-8b-instruct 8.2B Q8_0 11.1 GiB 30,464 — Fits
granite-guardian-3.2-8b-factuality-detection 8.2B Q8_0 11.1 GiB 30,464 — Fits
intent-aware-lfqa-llama3-8b-baseline 8.0B Q8_0 10.2 GiB 43,264 — Fits
intent-aware-lfqa-llama3-8b-intent-explicit 8.0B Q8_0 10.2 GiB 43,264 — Fits
intent-aware-lfqa-llama3-8b-intent-implicit 8.0B Q8_0 10.2 GiB 43,264 — Fits
intent-aware-lfqa-llama3-8b-multiview 8.0B Q8_0 10.2 GiB 43,264 — Fits
DeepSeek-R1-Distill-Llama-8B 8.0B Q8_0 10.2 GiB 43,264 — Fits
HARC-Llama-3.1-8B-Instruct 8.0B Q6_K 8.4 GiB 57,088 — Fits
Llama-3.1-8B-Instruct 8.0B Q6_K 8.4 GiB 57,088 — Fits
AprielGuard 7.9B Q6_K 7.9 GiB 78,080 — Fits
MiMo-Embodied-7B 7.6B Q6_K 8.1 GiB 53,248 — Fits
DeepSeek-R1-Distill-Qwen-7B 7.6B Q8_0 9.1 GiB 104,192 — Fits
Fara-7B 7.6B Q8_0 9.1 GiB 104,192 — Fits
HARC-Qwen2.5-7B-Instruct 7.6B Q6_K 7.5 GiB 32,768 — Fits
JanusCoderV-7B 7.6B Q8_0 9.1 GiB 104,192 — Fits
olmOCR-2-7B-1025 7.6B Q8_0 9.1 GiB 104,192 — Fits
Qwen2.5-7B-Instruct 7.6B Q8_0 9.1 GiB 32,768 — Fits
Qwen2.5-Coder-7B-Instruct 7.6B Q8_0 9.1 GiB 32,768 — Fits
Qwen2.5-VL-7B-Instruct 7.6B Q8_0 9.1 GiB 104,192 — Fits
Qwen2.5-VL-7B-Surg-CholecT50 7.6B Q8_0 9.1 GiB 104,192 — Fits
Spatial-SSRL-7B 7.6B Q6_K 7.5 GiB 128,000 — Fits
X-Reasoner-7B 7.6B Q6_K 7.5 GiB 128,000 — Fits
ZwZ-7B 7.6B Q6_K 7.5 GiB 128,000 — Fits
gemma-4-E4B 7.5B F16 11.0 GiB 131,072 — Fits
gemma-4-E4B-it 7.5B BF16 11.0 GiB 131,072 — Fits
Bielik-Minitron-7B-v3.0-Instruct 7.5B Q8_0 10.2 GiB 32,768 — Fits
ContextPilot-E4B 7.5B F16 10.9 GiB 131,072 — Fits
Olmo-3.1-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3.1-7B-RL-Zero-Math 7.3B Q8_0 12.7 GiB 12,032 — Fits
Olmo-3-7B-Instruct 7.3B Q8_0 12.7 GiB 12,032 — Fits
Olmo-3-7B-Instruct-DPO 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3-7B-Instruct-SFT 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3-7B-RL-Zero-General 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3-7B-RL-Zero-IF 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3-7B-RL-Zero-Math 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3-7B-RL-Zero-Mix 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3-7B-Think 7.3B Q8_0 12.7 GiB 12,032 — Fits
Olmo-3-7B-Think-DPO 7.3B Q6_K 11.0 GiB 15,104 — Fits
Olmo-3-7B-Think-SFT 7.3B Q6_K 11.0 GiB 15,104 — Fits
Mistral-7B-Instruct-v0.2 7.2B Q6_K 8.1 GiB 32,768 — Fits
Trinity-Nano-Base 6.1B (819M active) Q6_K 6.7 GiB 131,072 — Fits
Trinity-Nano-Base-Pre-Anneal 6.1B (819M active) Q6_K 6.4 GiB 4,096 — Fits
Trinity-Nano-Preview 6.1B (819M active) BF16 13.5 GiB 83,968 — Fits
Youtu-VL-4B-Instruct 4.9B Q6_K 5.9 GiB 32,768 — Fits
Holo-3.1-4B 4.8B F16 10.2 GiB 140,288 — Fits
gemma-4-E2B 4.6B Q6_K 3.5 GiB 131,072 — Fits
gemma-4-E2B-it 4.6B BF16 6.1 GiB 131,072 — Fits
AgentCPM-Explore 4.4B Q6_K 5.7 GiB 69,632 — Fits
CapRL-Qwen3VL-4B 4.4B F16 10.4 GiB 37,888 — Fits
Holo2-4B 4.4B F16 10.4 GiB 37,888 — Fits
intent-aware-lfqa-qwen3-4b-baseline 4.4B F16 10.4 GiB 37,888 — Fits
intent-aware-lfqa-qwen3-4b-intent-explicit 4.4B F16 10.4 GiB 37,888 — Fits
intent-aware-lfqa-qwen3-4b-intent-implicit 4.4B F16 10.4 GiB 37,888 — Fits
intent-aware-lfqa-qwen3-4b-multiview 4.4B F16 10.4 GiB 37,888 — Fits
Spatial-SSRL-Qwen3VL-4B 4.4B F16 10.4 GiB 37,888 — Fits
ZwZ-4B 4.4B Q6_K 5.7 GiB 69,632 — Fits
Fara1.5-4B 4.2B BF16 10.2 GiB 140,288 — Fits
FrogNano-4B-2609 4.2B BF16 10.2 GiB 140,288 — Fits
Qwen3.5-4B 4.2B BF16 10.2 GiB 140,288 — Fits
Qwen3.5-4B-Base 4.2B F16 10.2 GiB 140,288 — Fits
UserRepGen-4B 4.2B BF16 10.2 GiB 140,288 — Fits
Riva-Translate-4B-Instruct-v1.1 4.2B Q6_K 6.0 GiB 8,192 — Fits
GELab-Zero-4B-preview 4.0B BF16 10.4 GiB 37,888 — Fits
Qwen3-4B 4.0B Q8_0 6.7 GiB 40,960 — Fits
Qwen3-4B-Instruct-2507 4.0B F16 10.4 GiB 37,888 — Fits
Qwen3-VL-4B-Instruct 4.0B BF16 10.4 GiB 37,888 — Fits
Qwen3-VL-4B-Thinking 4.0B BF16 10.4 GiB 37,888 — Fits
NVIDIA-Nemotron-3-Nano-4B-BF16 4.0B BF16 8.7 GiB 262,144 — Fits
gemma-3-4b-it 3.9B BF16 9.9 GiB 131,072 — Fits
medgemma-1.5-4b-it 3.9B BF16 9.9 GiB 131,072 — Fits
Nemotron-3-Content-Safety 3.9B Q6_K 5.4 GiB 131,072 — Fits
translategemma-4b-it 3.9B F16 9.9 GiB 131,072 — Fits
Phi-4-mini-instruct 3.8B BF16 10.0 GiB 44,544 — Fits
Apertus-v1.1-4B 3.8B Q6_K 4.4 GiB 4,096 — Fits
Phi-3.5-mini-instruct 3.8B Q8_0 8.3 GiB 24,576 — Fits
granite-4.2-3b 3.7B BF16 8.6 GiB 82,688 — Fits
BitCPM-CANN-3B-unquantized 3.6B Q6_K 4.3 GiB 32,768 — Fits
kanana-2-3b-instruct 3.5B F16 8.6 GiB 32,768 — Fits
Ministral-3-3B-Instruct-2512 3.4B BF16 8.9 GiB 63,488 — Fits
Ministral-3-3B-Reasoning-2512 3.4B BF16 8.9 GiB 63,488 — Fits
granite-vision-4.1-4b 3.4B BF16 8.6 GiB 82,688 — Fits
granite-4.1-3b 3.4B BF16 8.6 GiB 82,688 — Fits
granite-guardian-4.0-3b-toxicity-ja 3.4B Q6_K 4.7 GiB 130,560 — Fits
Qwen2.5-3B-Instruct 3.4B Q8_0 4.8 GiB 32,768 — Fits
tiny-aya-earth 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) — Fits
tiny-aya-fire 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) — Fits
tiny-aya-global 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) — Fits
tiny-aya-water 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) — Fits
Llama-3.2-3B-Instruct 3.2B BF16 8.5 GiB 62,720 — Fits
AI21-Jamba-Reasoning-3B 3.2B BF16 7.3 GiB 262,144 — Fits
AI21-Jamba2-3B 3.2B BF16 7.3 GiB 262,144 — Fits
kanana-2-3b-base 3.2B Q6_K 4.9 GiB 32,768 — Fits
SmolLM3-3B 3.1B BF16 7.9 GiB 65,536 — Fits
SmolLM3-3B-GSM8K-SFT 3.1B Q6_K 4.3 GiB 65,536 — Fits
LFM2-2.6B-Exp 2.7B F16 6.5 GiB 128,000 — Fits
d1-3B 2.7B BF16 6.7 GiB 32,768 — Fits
LFM2.5-2.6B 2.7B BF16 6.7 GiB 131,072 — Fits
LFM2.5-2.6B-Base 2.7B Q6_K 3.6 GiB 128,000 — Fits
LFM2.5-VL-3B 2.7B BF16 6.7 GiB 32,768 — Fits
EuroMoE-2.6B-A0.6B-Instruct-2512 2.6B (498M active) Q6_K 3.6 GiB 32,768 — Fits
LFM2-2.6B-Longevity 2.6B F16 6.5 GiB 128,000 — Fits
LFM2-2.6B-Transcript 2.6B BF16 6.5 GiB 128,000 — Fits
LFM2-VL-3B 2.6B BF16 6.5 GiB 128,000 — Fits
MiniCPM5-2B 2.5B BF16 6.0 GiB 131,072 — Fits
MiniCPM5-2B-Base 2.5B Q6_K 3.4 GiB ≥ 262,144 (longer contexts not checked against measured logs) — Fits
CapRL-Qwen3VL-2B 2.0B F16 5.6 GiB 87,808 — Fits
HiPO-1.7B 2.0B Q6_K 3.6 GiB 40,960 — Fits
UI-Venus-1.5-2B 2.0B F16 5.6 GiB 87,808 — Fits
ZwZ-2B 2.0B F16 5.6 GiB 87,808 — Fits
Youtu-LLM-2B 2.0B Q6_K 3.2 GiB 131,072 — Fits
Youtu-LLM-2B-Base 2.0B Q6_K 3.2 GiB 131,072 — Fits
Qwen3.5-2B 1.9B BF16 5.4 GiB 262,144 — Fits
Qwen3.5-2B-Base 1.9B Q6_K 3.2 GiB 262,144 — Fits
Qwen3-1.7B 1.7B BF16 5.6 GiB 40,960 — Fits
Qwen3-VL-2B-Instruct 1.7B BF16 5.6 GiB 87,808 — Fits
Qwen3-VL-2B-Thinking 1.7B BF16 5.6 GiB 87,808 — Fits
SingGuard-2b 1.7B F16 5.6 GiB 87,808 — Fits
granite-4.0-1b 1.6B BF16 5.1 GiB 124,928 — Fits
Apertus-v1.1-1.5B 1.5B F16 3.8 GiB 4,096 — Fits
Apertus-v1.1-1.5B-Instruct 1.5B F16 3.8 GiB 4,096 — Fits
granite-4.0-h-1b 1.5B BF16 4.4 GiB 131,072 — Fits
Llama-3.2-1B-Instruct 1.2B BF16 4.0 GiB 131,072 — Fits
LFM2.5-1.2B-Base 1.2B BF16 3.7 GiB 128,000 — Fits
LFM2.5-1.2B-Instruct 1.2B BF16 3.7 GiB 128,000 — Fits
LFM2.5-1.2B-JP 1.2B F16 3.7 GiB 128,000 — Fits
LFM2.5-1.2B-JP-202606 1.2B F16 3.7 GiB 128,000 — Fits
LFM2.5-1.2B-Thinking 1.2B BF16 3.7 GiB 128,000 — Fits
LFM2.5-VL-1.6B 1.2B BF16 3.7 GiB 128,000 — Fits
LFM2.5-VL-1.6B-Extract 1.2B F16 3.7 GiB 128,000 — Fits
MiniCPM5-1B 1.1B Q6_K 2.2 GiB 131,072 — Fits
MiniCPM5-1B-Base 1.1B Q6_K 2.2 GiB 131,072 — Fits
MiniCPM5-1B-SFT 1.1B Q6_K 2.2 GiB 131,072 — Fits
Holo-3.1-0.8B 1.0B Q6_K 2.3 GiB 262,144 — Fits
MiniCPM-V-4.7-1B 1.0B F16 3.2 GiB 262,144 — Fits
gemma-3-1b-it 1.0B BF16 3.6 GiB 32,768 — Fits
Qwen3.5-0.8B 752M BF16 3.2 GiB 262,144 — Fits
Qwen3.5-0.8B-Base 752M Q6_K 2.3 GiB 262,144 — Fits
MiniCPM-V-4.6 752M F16 3.2 GiB 262,144 — Fits
MiniCPM-V-4.6-Thinking 752M F16 3.2 GiB 262,144 — Fits
Qwen3-0.6B 752M BF16 3.4 GiB 40,960 — Fits
HunyuanOCR 539M F16 3.1 GiB 32,768 — Fits
LFM2.5-350M 354M BF16 2.1 GiB 128,000 — Fits
LFM2.5-Encoder-350M-Diffusion 354M Q6_K 1.7 GiB 128,000 — Fits
LFM2.5-VL-450M 354M BF16 2.1 GiB 128,000 — Fits
LFM2.5-VL-450M-Extract 354M F16 2.1 GiB 128,000 — Fits
granite-4.0-350m 352M BF16 2.2 GiB 32,768 — Fits
granite-4.0-h-350m 340M BF16 2.1 GiB 32,768 — Fits
functiongemma-270m-it 268M BF16 2.1 GiB 32,768 — Fits
LFM2.5-230M 230M BF16 1.8 GiB 128,000 — Fits

Borderline models

Within the estimate error range: it may fit or it may not. Try a shorter context or a lower quantization.

Context 8,192 tokens. No quantization of these models fits; the one shown is the highest that is borderline.
Model Parameters Highest borderline quantization Available memory needed for “Fits” Result
Qwen3.5-35B-A3B 34.7B (2.9B active) Q3_K_M 17.6 GiB Tight
DeepSeek-R1-Distill-Qwen-32B 32.8B Q3_K_M 18.7 GiB Tight
Qwen2.5-32B-Instruct 32.8B Q3_K_M 18.7 GiB Tight
Qwen2.5-Coder-32B-Instruct 32.8B Q3_K_M 18.7 GiB Tight
Qwen3-VL-32B-Instruct 32.8B Q3_K_M 18.8 GiB Tight
Qwen3-VL-32B-Thinking 32.8B Q3_K_M 18.8 GiB Tight
Olmo-3.1-32B-Instruct 32.2B IQ4_XS 20.1 GiB Tight
Olmo-3.1-32B-Think 32.2B IQ4_XS 20.1 GiB Tight
Olmo-3-32B-Think 32.2B IQ4_XS 20.1 GiB Tight
Holotron4-30B-A3B 31.6B (3.2B active) Q4_0 19.0 GiB Tight
Nemotron-Cascade-2-30B-A3B 31.6B (3.2B active) Q4_0 19.2 GiB Tight
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 31.6B (3.2B active) Q4_0 19.0 GiB Tight
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.3 GiB Tight
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.2 GiB Tight
NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.0 GiB Tight
gemma-4-31B 30.7B Q3_K_M 20.9 GiB Tight
gemma-4-31B-it 30.7B IQ4_XS 21.9 GiB Tight
Ising-Calibration-1.5-31B-BF16 30.7B Q3_K_M 21.5 GiB Tight
Qwen3.5-27B 26.9B Q4_K_M 18.4 GiB Tight
Qwen3.6-27B 26.9B Q4_K_M 18.4 GiB Tight
gemma-4-12B 11.9B Q8_0 15.6 GiB Tight

Models that don’t fit on one AMD Radeon RX 7800 XT

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
MiniCPM-V-4.7-35B-A3B 34.7B (2.9B active) IQ4_XS 20.0 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
EXAONE-4.5-33B 32.5B IQ4_XS 20.4 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Llama-3.1-70B-Instruct 70.6B IQ2_XXS 22.3 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3-Coder-Next-Base 79.7B (3.6B active) IQ2_XXS 22.3 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3-32B 32.8B Q4_K_M 22.4 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
QwQ-32B 32.8B Q4_K_M 22.5 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 31.6B (3.2B active) Q4_K_M 23.3 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
KAT-Dev-72B-Exp 72.7B IQ2_XXS 28.5 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Solar-Open-100B 103B (11.2B active) IQ2_XXS 29.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
DeepSeek-R1-Distill-Llama-70B 70.6B Q2_K 29.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Llama-3.3-70B-Instruct 70.6B Q2_K 29.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Next-80B-A3B-Instruct 79.7B (3.6B active) Q2_K 30.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen2.5-72B-Instruct 73.0B Q2_K 30.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Coder-Next 79.7B (3.6B active) Q2_K 30.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.5-Air-REAP-82B-A12B 81.9B (12.8B active) IQ2_XXS 31.1 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Step-3.5-Flash-REAP-121B-A11B 121B (11.4B active) IQ2_XXS 32.9 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Mistral-Small-4-119B-2603 119B (6.1B active) IQ2_XXS 34.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3.5-122B-A10B 122B (9.0B active) IQ2_XXS 35.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen-AgentWorld-35B-A3B 34.7B (2.9B active) Q8_0 37.6 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2.5-REAP-139B-A10B 139B (10.4B active) IQ2_XXS 39.2 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
INTELLECT-3 107B (12.8B active) IQ2_XXS 39.6 GiB 3 identical cards (default even split) are expected to fit. Doesn't fit
Step-3.5-Flash-REAP-149B-A11B 149B (11.4B active) IQ2_XXS 40.1 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Llama-4-Scout-17B-16E-Instruct 108B (16.1B active) Q2_K 41.5 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.5-Air 107B (12.8B active) Q2_K 45.6 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.6V 107B (12.8B active) Q2_K 45.6 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Step-3.5-Flash 197B (11.5B active) IQ2_XXS 48.9 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Devstral-2-123B-Instruct-2512 125B Q2_K 49.3 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Mistral-Medium-3.5-128B 125B Q2_K 49.3 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 121B (12.2B active) IQ2_XXS 49.8 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3-Super-120B-A12B-BF16 121B (12.2B active) IQ2_XXS 51.0 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
gpt-oss-120b 117B (5.1B active) Q2_K 62.8 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2.7 229B (10.4B active) IQ2_XXS 62.9 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Baichuan-M3-235B 235B (21.6B active) IQ2_XXS 63.2 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Holo2-235B-A22B 235B (21.6B active) IQ2_XXS 63.2 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Nemotron-235B-A22B-GenRM 235B (21.6B active) IQ2_XXS 63.2 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
command-a-plus-05-2026-bf16 218B (25.0B active) IQ2_XXS 63.6 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 121B (12.2B active) Q4_0 71.8 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.7-REAP-268B-A32B 269B (32.8B active) IQ2_XXS 73.0 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Step-3.7-Flash 197B (11.5B active) IQ3_XXS 76.1 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Hy3 295B (20.2B active) IQ2_XXS 82.2 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiMo-V2.5 309B (14.8B active) IQ2_XXS 82.4 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.7-REAP-218B-A32B 218B (32.8B active) Q2_K 82.9 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2 229B (10.4B active) Q2_K 84.9 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2.1 229B (10.4B active) Q2_K 84.9 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2.5 229B (10.4B active) Q2_K 84.9 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-235B-A22B-Instruct-2507 235B (21.6B active) Q2_K 86.7 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-VL-235B-A22B-Instruct 235B (21.6B active) Q2_K 86.7 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-5.3-Flash-BF16 313B (16.7B active) IQ2_XXS 92.0 GiB Borderline with 8 cards. Doesn't fit
Laguna-S-2.1 118B (8.1B active) Q4_K_M 95.9 GiB Borderline with 8 cards. Doesn't fit
Trinity-Large-Base 399B (12.8B active) IQ2_XXS 96.4 GiB Borderline with 8 cards. Doesn't fit
Trinity-Large-TrueBase 399B (12.8B active) IQ2_XXS 96.4 GiB Borderline with 8 cards. Doesn't fit
GLM-4.6-REAP-268B-A32B 269B (32.8B active) Q2_K 100.9 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Trinity-Large-Thinking 399B (12.8B active) IQ2_XXS 107.1 GiB Borderline with 8 cards. Doesn't fit
MiMo-V2-Flash 309B (14.8B active) Q2_K 111.6 GiB Borderline with 8 cards. Doesn't fit
Intern-S2-397B 396B (16.3B active) IQ2_XXS 114.3 GiB Borderline with 8 cards. Doesn't fit
MiMo-V2.6-Flash-MOPD 309B (14.8B active) Q2_K 124.9 GiB Borderline with 8 cards. Doesn't fit
MiMo-V2.6-Flash-RL 309B (14.8B active) Q2_K 124.9 GiB Borderline with 8 cards. Doesn't fit
K-EXAONE-236B-A23B 237B (22.7B active) IQ4_XS 126.3 GiB Borderline with 8 cards. Doesn't fit
GLM-4.5 353B (32.9B active) Q2_K 130.7 GiB Borderline with 8 cards. Doesn't fit
GLM-4.7 353B (32.9B active) Q2_K 130.7 GiB Borderline with 8 cards. Doesn't fit
Qwen3-Coder-REAP-363B-A35B 363B (34.5B active) Q2_K 132.7 GiB Borderline with 8 cards. Doesn't fit
Qwen3-235B-A22B 235B (21.6B active) Q4_K_M 141.9 GiB Borderline with 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

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

Detailed pages for this GPU

Other devices with 16 GB