更新日志
本页面由 AI 自动撰写和翻译，并由软件对照来源进行检查，没有人工编辑。规格来自所列来源；显存需求和速度是按已公布的公式计算出的估算值。 我们如何使用 AI
2026年10月19日
数值有变化的模型
- EXAONE-4.5-33B
- FrogNano-4B-2609
- GLM-4.5
- GLM-4.5-Air
- GLM-4.5-Air-REAP-82B-A12B
- GLM-5.1
- GLM-5.3-Flash-BF16
- Hy3
- Intern-S2-397B
- K-EXAONE-236B-A23B
- MiMo-V2.5
- MiMo-V2.5-Pro
- MiniMax-M2
- MiniMax-M2.1
- MiniMax-M2.5
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
- Qwen3.8-3.6-27B-blend
数值有变动的显卡
- NVIDIA GeForce GTX 1070
- NVIDIA GeForce RTX 3050 8GB
- NVIDIA GeForce RTX 3060 Ti
- NVIDIA GeForce RTX 3070 Ti
- NVIDIA GeForce RTX 4070
- NVIDIA P100
- NVIDIA Tesla V100 32GB
已暂缓的显卡（数值已隐藏；原因见该条目页面）
2026年10月18日
新增模型
- AesCode-32B
- AesCode-8B
- AgentCPM-Explore
- AI21-Jamba-Reasoning-3B
- AI21-Jamba2-3B
- AI21-Jamba2-Mini
- Apertus-v1.1-1.5B
- Apertus-v1.1-1.5B-Instruct
- Apertus-v1.1-4B
- Apriel-1.6-15b-Thinker
- AprielGuard
- ArmorOCR
- AstaBrief_8B
- AutoGLM-Phone-9B
- AutoGLM-Phone-9B-Multilingual
- Baichuan-M3-235B
- Beam-1.0-501B-A23B
- Bielik-11B-v3.0-Instruct
- Bielik-Minitron-7B-v3.0-Instruct
- BitCPM-CANN-3B-unquantized
- CapRL-Qwen3VL-2B
- CapRL-Qwen3VL-4B
- cogito-671b-v2.1
- command-a-plus-05-2026-bf16
- ContextPilot-14B
- ContextPilot-8B
- ContextPilot-E4B
- Cosmos-Reason2-32B
- Cosmos-Reason2-8B
- d1-3B
- DeepSeek-R1
- DeepSeek-R1-0528-Qwen3-8B
- DeepSeek-R1-Distill-Llama-70B
- DeepSeek-R1-Distill-Llama-8B
- DeepSeek-R1-Distill-Qwen-14B
- DeepSeek-R1-Distill-Qwen-32B
- DeepSeek-R1-Distill-Qwen-7B
- DeepSeek-V3
- DeepSeek-V3.1
- DeepSeek-V3.2
- Devstral-2-123B-Instruct-2512
- Devstral-Small-2-24B-Instruct-2512
- EuroLLM-22B-2512
- EuroLLM-22B-Instruct-2512
- EuroLLM-9B-Instruct-2512
- EuroMoE-2.6B-A0.6B-Instruct-2512
- EXAONE-4.5-33B
- Fara-7B
- Fara1.5-27B
- Fara1.5-4B
- Fara1.5-9B
- FrogBoss-32B-2510
- FrogMini-14B-2510
- FrogNano-4B-2609
- functiongemma-270m-it
- GELab-Zero-4B-preview
- gemma-2-27b-it
- gemma-2-9b-it
- gemma-3-12b-it
- gemma-3-1b-it
- gemma-3-27b-it
- gemma-3-4b-it
- gemma-4-12B
- gemma-4-12B-it
- gemma-4-26B-A4B
- gemma-4-26B-A4B-it
- gemma-4-31B
- gemma-4-31B-it
- gemma-4-E2B
- gemma-4-E2B-it
- gemma-4-E4B
- gemma-4-E4B-it
- GLM-4.5
- GLM-4.5-Air
- GLM-4.5-Air-REAP-82B-A12B
- GLM-4.6-REAP-268B-A32B
- GLM-4.6V
- GLM-4.6V-Flash
- GLM-4.7
- GLM-4.7-Flash
- GLM-4.7-Flash-REAP-23B-A3B
- GLM-4.7-REAP-218B-A32B
- GLM-4.7-REAP-268B-A32B
- GLM-5
- GLM-5.1
- GLM-5.2
- GLM-5.3
- GLM-5.3-Flash
- GLM-5.3-Flash-BF16
- gpt-oss-120b
- gpt-oss-20b
- granite-3.3-8b-instruct
- granite-4.0-1b
- granite-4.0-350m
- granite-4.0-h-1b
- granite-4.0-h-350m
- granite-4.1-30b
- granite-4.1-3b
- granite-4.1-8b
- granite-4.2-30b
- granite-4.2-3b
- granite-4.2-8b
- granite-guardian-3.2-8b-factuality-detection
- granite-guardian-4.0-3b-toxicity-ja
- granite-guardian-4.1-8b
- granite-vision-4.1-4b
- HARC-Llama-3.1-8B-Instruct
- HARC-Qwen2.5-7B-Instruct
- Hermes-4.3-36B
- HiPO-1.7B
- Holo-3.1-0.8B
- Holo-3.1-35B-A3B
- Holo-3.1-4B
- Holo-3.1-9B
- Holo2-235B-A22B
- Holo2-30B-A3B
- Holo2-4B
- Holo2-8B
- Holo3-35B-A3B
- Holo4-27B
- Holo4-35B-A3B
- Holotron4-30B-A3B
- HunyuanOCR
- Hy3
- INTELLECT-3
- intent-aware-lfqa-llama3-8b-baseline
- intent-aware-lfqa-llama3-8b-intent-explicit
- intent-aware-lfqa-llama3-8b-intent-implicit
- intent-aware-lfqa-llama3-8b-multiview
- intent-aware-lfqa-qwen3-4b-baseline
- intent-aware-lfqa-qwen3-4b-intent-explicit
- intent-aware-lfqa-qwen3-4b-intent-implicit
- intent-aware-lfqa-qwen3-4b-multiview
- intent-aware-lfqa-qwen3-8b-baseline
- intent-aware-lfqa-qwen3-8b-intent-explicit
- intent-aware-lfqa-qwen3-8b-intent-implicit
- intent-aware-lfqa-qwen3-8b-multiview
- Intern-S2-397B
- Ising-Calibration-1-35B-A3B
- Ising-Calibration-1.5-31B-BF16
- JanusCoder-14B
- JanusCoder-8B
- JanusCoderV-7B
- K-EXAONE-236B-A23B
- kanana-2-3b-base
- kanana-2-3b-instruct
- KAT-Coder-V2.5-Dev
- KAT-Dev-72B-Exp
- Kimi-K2.5
- Kimi-K2.6
- Kimi-K2-Instruct
- Kimi-K2-Thinking
- Kimi-Linear-48B-A3B-Base
- Kimi-Linear-48B-A3B-Instruct
- Kimi-Linear-REAP-35B-A3B-Instruct
- Laguna-S-2.1
- Laguna-XS-2.1
- LFM2-2.6B-Exp
- LFM2-2.6B-Longevity
- LFM2-2.6B-Transcript
- LFM2-24B-A2B
- LFM2.5-1.2B-Base
- LFM2.5-1.2B-Instruct
- LFM2.5-1.2B-JP
- LFM2.5-1.2B-JP-202606
- LFM2.5-1.2B-Thinking
- LFM2.5-2.6B
- LFM2.5-2.6B-Base
- LFM2.5-230M
- LFM2.5-24B-A2B
- LFM2.5-350M
- LFM2.5-8B-A1B
- LFM2.5-Encoder-350M-Diffusion
- LFM2.5-VL-1.6B
- LFM2.5-VL-1.6B-Extract
- LFM2.5-VL-3B
- LFM2.5-VL-450M
- LFM2.5-VL-450M-Extract
- LFM2-8B-A1B
- LFM2-VL-3B
- Ling-1T
- Llama-3.1-70B-Instruct
- Llama-3.1-8B-Instruct
- Llama-3.2-1B-Instruct
- Llama-3.2-3B-Instruct
- Llama-3.3-70B-Instruct
- Llama-4-Scout-17B-16E-Instruct
- MathForm-8B
- medgemma-1.5-4b-it
- Mellum2.1-12B-A2.5B-Thinking
- Mellum2-12B-A2.5B-Base
- Mellum2-12B-A2.5B-Instruct
- Mellum2-12B-A2.5B-Instruct-SFT
- Mellum2-12B-A2.5B-Thinking
- Mellum2-12B-A2.5B-Thinking-SFT
- MiMo-Embodied-7B
- MiMo-V2.5
- MiMo-V2.5-Pro
- MiMo-V2.6-Distill-Qwen-9B
- MiMo-V2.6-Flash-MOPD
- MiMo-V2.6-Flash-RL
- MiMo-V2.6-Pro-MOPD
- MiMo-V2.6-Pro-RL
- MiMo-V2-Flash
- MiniCPM-o-4_5
- MiniCPM-V-4.6
- MiniCPM-V-4.6-Thinking
- MiniCPM-V-4.7-1B
- MiniCPM-V-4.7-35B-A3B
- MiniCPM5-1B
- MiniCPM5-1B-Base
- MiniCPM5-1B-SFT
- MiniCPM5-2B
- MiniCPM5-2B-Base
- MiniMax-M2
- MiniMax-M2.1
- MiniMax-M2.5
- MiniMax-M2.5-REAP-139B-A10B
- MiniMax-M2.7
- Ministral-3-14B-Instruct-2512
- Ministral-3-14B-Reasoning-2512
- Ministral-3-3B-Instruct-2512
- Ministral-3-3B-Reasoning-2512
- Ministral-3-8B-Instruct-2512
- Ministral-3-8B-Reasoning-2512
- Mistral-7B-Instruct-v0.2
- Mistral-Large-3-675B-Instruct-2512
- Mistral-Medium-3.5-128B
- Mistral-Nemo-Instruct-2407
- Mistral-Small-3.2-24B-Instruct-2506
- Mistral-Small-4-119B-2603
- Muse-Glimmer-30B
- Muse-Spark-Open-816B-A42B
- Nemotron-3-Content-Safety
- Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
- Nemotron-Cascade-14B-Thinking
- Nemotron-Cascade-2-30B-A3B
- Nemotron-Cascade-8B
- Nemotron-Cascade-8B-Thinking
- Nemotron-Orchestrator-8B
- Nemotron-Terminal-14B
- Nemotron-Terminal-32B
- Nemotron-Terminal-8B
- North-Mini-Code-1.0
- NousCoder-14B
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
- NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- NVIDIA-Nemotron-3-Nano-4B-BF16
- NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16
- NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16
- NVIDIA-Nemotron-Nano-9B-v2
- Olmo-3.1-32B-Instruct
- Olmo-3.1-32B-Instruct-DPO
- Olmo-3.1-32B-Think
- Olmo-3.1-7B-RL-Zero-Code
- Olmo-3.1-7B-RL-Zero-Math
- Olmo-3-1125-32B
- Olmo-3-32B-Think
- Olmo-3-32B-Think-DPO
- Olmo-3-32B-Think-SFT
- Olmo-3-7B-Instruct
- Olmo-3-7B-Instruct-DPO
- Olmo-3-7B-Instruct-SFT
- Olmo-3-7B-RL-Zero-Code
- Olmo-3-7B-RL-Zero-General
- Olmo-3-7B-RL-Zero-IF
- Olmo-3-7B-RL-Zero-Math
- Olmo-3-7B-RL-Zero-Mix
- Olmo-3-7B-Think
- Olmo-3-7B-Think-DPO
- Olmo-3-7B-Think-SFT
- olmOCR-2-7B-1025
- OptiMind-SFT
- Phi-3.5-mini-instruct
- phi-4
- Phi-4-mini-instruct
- Qwen-AgentWorld-35B-A3B
- Qwen2.5-14B-Instruct
- Qwen2.5-32B-Instruct
- Qwen2.5-3B-Instruct
- Qwen2.5-72B-Instruct
- Qwen2.5-7B-Instruct
- Qwen2.5-Coder-32B-Instruct
- Qwen2.5-Coder-7B-Instruct
- Qwen2.5-VL-7B-Instruct
- Qwen2.5-VL-7B-Surg-CholecT50
- Qwen3-0.6B
- Qwen3-1.7B
- Qwen3-14B
- Qwen3-235B-A22B
- Qwen3-235B-A22B-Instruct-2507
- Qwen3-30B-A3B
- Qwen3-30B-A3B-Instruct-2507
- Qwen3-32B
- Qwen3-4B
- Qwen3-4B-Instruct-2507
- Qwen3.5-0.8B
- Qwen3.5-0.8B-Base
- Qwen3.5-122B-A10B
- Qwen3.5-27B
- Qwen3.5-2B
- Qwen3.5-2B-Base
- Qwen3.5-35B-A3B
- Qwen3.5-35B-A3B-Base
- Qwen3.5-397B-A17B
- Qwen3.5-4B
- Qwen3.5-4B-Base
- Qwen3.5-9B
- Qwen3.5-9B-Base
- Qwen3.6-27B
- Qwen3.6-35B-A3B
- Qwen3.8-2.4T-A95B
- Qwen3.8-27B
- Qwen3.8-3.6-27B-blend
- Qwen3-8B
- Qwen3-Coder-30B-A3B-Instruct
- Qwen3-Coder-480B-A35B-Instruct
- Qwen3-Coder-Next
- Qwen3-Coder-Next-Base
- Qwen3-Coder-REAP-25B-A3B
- Qwen3-Coder-REAP-363B-A35B
- Qwen3-Nemotron-14B-BRRM
- Qwen3-Nemotron-235B-A22B-GenRM
- Qwen3-Nemotron-8B-BRRM
- Qwen3-Next-80B-A3B-Instruct
- Qwen3-VL-235B-A22B-Instruct
- Qwen3-VL-2B-Instruct
- Qwen3-VL-2B-Thinking
- Qwen3-VL-30B-A3B-Instruct
- Qwen3-VL-32B-Instruct
- Qwen3-VL-32B-Thinking
- Qwen3-VL-4B-Instruct
- Qwen3-VL-4B-Thinking
- Qwen3-VL-8B-Instruct
- Qwen3-VL-8B-Thinking
- QwQ-32B
- Riva-Translate-4B-Instruct-v1.1
- RLVR-8B-0926
- rnj-1-instruct
- SERA-32B
- SingGuard-2b
- SmolLM3-3B
- SmolLM3-3B-GSM8K-SFT
- Solar-Open-100B
- Spatial-SSRL-7B
- Spatial-SSRL-Qwen3VL-4B
- Step-3.5-Flash
- Step-3.5-Flash-REAP-121B-A11B
- Step-3.5-Flash-REAP-149B-A11B
- Step-3.7-Flash
- Step3-VL-10B-Base
- tiny-aya-earth
- tiny-aya-fire
- tiny-aya-global
- tiny-aya-water
- translategemma-12b-it
- translategemma-27b-it
- translategemma-4b-it
- Trinity-Large-Base
- Trinity-Large-Thinking
- Trinity-Large-TrueBase
- Trinity-Mini
- Trinity-Mini-Base
- Trinity-Mini-Base-Pre-Anneal
- Trinity-Nano-Base
- Trinity-Nano-Base-Pre-Anneal
- Trinity-Nano-Preview
- UI-Mate-27B
- UI-Mate-9B
- UI-Mate-democua-27B
- UI-Venus-1.5-2B
- UI-Venus-1.5-30B-A3B
- UI-Venus-1.5-8B
- UI-Venus-2-9B
- UserRepGen-4B
- WebWorld-14B
- WebWorld-32B
- WebWorld-8B
- X-Reasoner-7B
- Youtu-LLM-2B
- Youtu-LLM-2B-Base
- Youtu-VL-4B-Instruct
- ZwZ-2B
- ZwZ-4B
- ZwZ-7B
- ZwZ-8B
新增显卡
- AMD Instinct MI210
- AMD Instinct MI300A
- AMD Instinct MI300X
- AMD Instinct MI325X
- AMD Instinct MI355X
- AMD Instinct MI350X
- AMD Radeon AI PRO R9700
- AMD Radeon Pro V520
- AMD Radeon PRO W7800 32GB
- AMD Radeon PRO W7800 48GB
- AMD Radeon PRO W7900
- AMD Radeon RX 7700 XT
- AMD Radeon RX 7800 XT
- AMD Radeon RX 7900 GRE
- AMD Radeon RX 7900 XT
- AMD Radeon RX 7900 XTX
- NVIDIA B100
- NVIDIA B200
- NVIDIA B300
- NVIDIA GeForce GTX 1050 Ti
- NVIDIA GeForce GTX 1060
- NVIDIA GeForce GTX 1070
- NVIDIA GeForce GTX 1070 Ti
- NVIDIA GeForce GTX 1080
- NVIDIA GeForce GTX 1080 Ti
- NVIDIA GeForce GTX 1650
- NVIDIA GeForce GTX 1660
- NVIDIA GeForce GTX 1660 SUPER
- NVIDIA GeForce RTX 2060 6GB
- NVIDIA GeForce RTX 2060 SUPER
- NVIDIA GeForce RTX 2070
- NVIDIA GeForce RTX 2080
- NVIDIA GeForce RTX 2080 Ti
- NVIDIA GeForce RTX 3050 8GB
- NVIDIA GeForce RTX 3060 12GB
- NVIDIA GeForce RTX 3060 Ti
- NVIDIA GeForce RTX 3070
- NVIDIA GeForce RTX 3070 Ti
- NVIDIA GeForce RTX 3080 10GB
- NVIDIA GeForce RTX 3080 Ti
- NVIDIA GeForce RTX 3090
- NVIDIA GeForce RTX 3090 Ti
- NVIDIA GeForce RTX 4060
- NVIDIA GeForce RTX 4060 Ti 16GB
- NVIDIA GeForce RTX 4070
- NVIDIA GeForce RTX 4070 Ti
- NVIDIA GeForce RTX 4070 Ti SUPER
- NVIDIA GeForce RTX 4080
- NVIDIA GeForce RTX 5060
- NVIDIA GeForce RTX 5060 Ti 16GB
- NVIDIA GeForce RTX 5070
- NVIDIA GeForce RTX 5070 Ti
- NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 5090
- NVIDIA H100 NVL
- NVIDIA H100 PCIe
- NVIDIA H200 SXM
- NVIDIA L4
- NVIDIA L40
- NVIDIA P100
- NVIDIA P4
- NVIDIA Tesla P40
- NVIDIA Tesla V100 32GB