Graphics cards
Which AI models run on the RTX 4080 (16 GB)?
The RTX 4080 (16 GB) has 16 GB of memory, about 15.0 GB of it usable for a model, and 717 GB/s of memory bandwidth. 51 of the 110 models in our catalog run on it at 4-bit or better.
Data as of 2 November 2026
Models that run on it
| Model | Best build | Memory | Speed |
|---|---|---|---|
| Nemotron Nano 9B v29B | Q8_0 | 10.8 GB | ~41 tok/s our est. |
| Qwen3.5 9B Instruct9B | Q8_0 | 12.0 GB | ~68 tok/s ModelFit est. |
| Qwen2.5 7B Instruct7B | Q4_K_M | 6.6 GB | ~116 tok/s ModelFit est. |
| Gemma 3 4B Instruct4B | Q8_0 | 5.0 GB | ~121 tok/s ModelFit est. |
| Qwen2.5 14B Instruct14B | Q4_K_M | 12.3 GB | ~62 tok/s ModelFit est. |
| Phi-3 Medium 14B14B | Q4_K_M | 12.3 GB | ~36 tok/s our est. |
| Phi-4 14B14B | Q4_K_M | 12.8 GB | ~60 tok/s ModelFit est. |
| Qwen2.5 Coder 14B14B | Q4_K_M | 12.3 GB | ~62 tok/s ModelFit est. |
| Qwen3 14B14B | Q4_K_M | 12.3 GB | ~61 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 14B14B | Q4_K_M | 12.3 GB | ~62 tok/s ModelFit est. |
| Ministral 3 14B13.5B | Q4_K_M | 10.3 GB | ~62 tok/s ModelFit est. |
| Mellum2.1 12B-A2.5B Thinking12.1B MoE | Q4_K_M | 9.3 GB | ~236 tok/s our est. |
| Mistral Nemo 12B12B | Q8_0 | 13.4 GB | ~46 tok/s ModelFit est. |
| Gemma 3 12B Instruct12B | Q4_K_M | 10.7 GB | ~72 tok/s ModelFit est. |
| Gemma 4 12B12B | Q8_0 | 14.1 GB | ~45 tok/s ModelFit est. |
| GLM-4-9B-Chat9.4B | Q8_0 | 11.2 GB | ~61 tok/s ModelFit est. |
| Gemma 2 9B Instruct9B | Q4_K_M | 8.2 GB | ~78 tok/s ModelFit est. |
| Ornith 1.0 9B9B | Q4_K_M | 6.7 GB | ~106 tok/s ModelFit est. |
| MiMo-V2.6-Distill-Qwen-9B9B | Q4_K_M | 6.9 GB | ~103 tok/s ModelFit est. |
| Jebadiah 9B9B | Q8_0 | 11.0 GB | ~66 tok/s ModelFit est. |
| Granite 4.2 8B8.8B | Q4_K_M | 6.1 GB | ~95 tok/s ModelFit est. |
| Granite Switch 4.1 8B8.8B | Q4_K_M | 7.6 GB | ~79 tok/s ModelFit est. |
| MiniCPM-V 4.5 8B8.7B | Q4_K_M | 6.8 GB | ~103 tok/s ModelFit est. |
| Ministral 3 8B8.4B | Q4_K_M | 7.1 GB | ~89 tok/s ModelFit est. |
| LFM2.5 8B-A1B8.3B MoE | Q4_K_M | 6.6 GB | ~250 tok/s ModelFit est. |
| Llama 3.1 8B Instruct8B | Q8_0 | 9.2 GB | ~67 tok/s ModelFit est. |
| Qwen3 8B8B | Q8_0 | 9.3 GB | ~65 tok/s ModelFit est. |
| Granite 4.1 8B Instruct8B | Q4_K_M | 6.6 GB | ~91 tok/s ModelFit est. |
| Mistral 7B Instruct7B | Q8_0 | 8.4 GB | ~70 tok/s ModelFit est. |
| Qwen2.5 Coder 7B7B | Q4_K_M | 6.6 GB | ~116 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 7B7B | Q8_0 | 8.7 GB | ~73 tok/s ModelFit est. |
| Gemma 4 E4B4.5B | Q8_0 | 8.7 GB | ~107 tok/s ModelFit est. |
| Qwen3.5 4B Instruct4B | Q8_0 | 5.4 GB | ~115 tok/s ModelFit est. |
| NVIDIA Nemotron 3.5 Bolt E4B4B | Q4_K_M | 9.1 GB | ~132 tok/s ModelFit est. |
| Phi-3 Mini 3.8B3.8B | Q4_K_M | 4.3 GB | ~123 tok/s our est. |
| Phi-4 Mini 3.8B3.8B | Q8_0 | 4.9 GB | ~115 tok/s ModelFit est. |
| Granite 4.2 3B3.7B | Q4_K_M | 3.2 GB | ~191 tok/s ModelFit est. |
| Ministral 3 3B3.4B | Q4_K_M | 4.1 GB | ~148 tok/s ModelFit est. |
| Qwen2.5 3B Instruct3B | Q4_K_M | 3.6 GB | ~214 tok/s ModelFit est. |
| Llama 3.2 3B Instruct3B | Q4_K_M | 3.6 GB | ~187 tok/s ModelFit est. |
| Granite 4.1 3B Instruct3B | Q4_K_M | 3.0 GB | ~191 tok/s ModelFit est. |
| Gemma 4 E2B2.3B | Q8_0 | 5.7 GB | ~214 tok/s ModelFit est. |
| Gemma 2 2B Instruct2B | Q4_K_M | 2.8 GB | ~209 tok/s ModelFit est. |
| Qwen3.5 2B Instruct2B | Q4_K_M | 2.8 GB | ~216 tok/s ModelFit est. |
| LFM3 1.7B1.73B | Q4_K_M | 2.1 GB | ~313 tok/s ModelFit est. |
| Qwen2.5 1.5B Instruct1.5B | Q4_K_M | 2.5 GB | ~320 tok/s ModelFit est. |
| Llama 3.2 1B Instruct1B | Q4_K_M | 2.0 GB | ~349 tok/s ModelFit est. |
| Gemma 3 1B Instruct1B | Q8_0 | 2.0 GB | ~322 tok/s ModelFit est. |
| Qwen3.5 0.8B Instruct0.8B | Q4_K_M | 1.8 GB | ~366 tok/s ModelFit est. |
| Qwen2.5 0.5B Instruct0.5B | Q4_K_M | 1.8 GB | ~481 tok/s ModelFit est. |
| SmolLM2 360M0.36B | Q4_K_M | 1.5 GB | ~358 tok/s ModelFit est. |
Speeds come from ModelFit's estimates (CC BY 4.0) where it covers the model, otherwise from our bandwidth formula. Method
Fits only at 3-bit or lower
Too big for this machine
gpt-oss-20b (15.1 GB), LFM2 24B-A2B Instruct (15.3 GB), Mistral Small 3.1 (16.4 GB), Devstral Small 2 24B (16.6 GB), Gemma 4 26B-A4B (17.4 GB), Qwen3.5 27B Instruct (17.4 GB), Qwen3.8-27B (17.9 GB), Granite 4.2 30B (17.9 GB), Jebadiah 27B (18.2 GB), Muse Glimmer 30B (18.3 GB), Mistral Small 22B (18.4 GB), AREX-2 27B (18.6 GB) and more.
Questions
What is the best AI model for the RTX 4080 (16 GB)?
Qwen3.5 9B Instruct at Q8_0: the largest model on our shortlist of current models that runs at 4-bit or better at a usable speed (about 68 tok/s, ModelFit est.).
How much memory can a model use on the RTX 4080 (16 GB)?
About 15.0 GB of the 16 GB.
How fast is the RTX 4080 (16 GB) for local LLMs?
Decode speed is limited by memory bandwidth: 717 GB/s. A model that reads 10 GB per token runs at under 72 tokens per second.