Graphics cards
Which AI models run on the RTX 3090 (24 GB)?
The RTX 3090 (24 GB) has 24 GB of memory, about 23 GB of it usable for a model, and 936 GB/s of memory bandwidth. 80 of the 110 models in our catalog run on it at 4-bit or better.
Data as of 2 November 2026 · Vendor specs
24 GBmemory
~23 GB usable for a model
936 GB/sbandwidth, sets the speed
80models run at 4-bit or better
Models that run on it
| Model | Best build | Memory | Speed |
|---|---|---|---|
| Gemma 4 31B30.7B | Q4_K_M | 21 GB | ~37 tok/s ModelFit est. |
| Qwen3-Coder-30B-A3B30.5B MoE | Q4_K_M | 20 GB | ~166 tok/s ModelFit est. |
| Nemotron 3 Nano 30B-A3B30B MoE | Q4_K_M | 19.6 GB | ~283 tok/s our est. |
| Qwen3.8-27B27.3B | Q4_K_M | 17.9 GB | ~45 tok/s ModelFit est. |
| Gemma 4 26B-A4B25.2B MoE | Q4_K_M | 17.4 GB | ~147 tok/s ModelFit est. |
| gpt-oss-20b21B MoE | MXFP4 | 15.1 GB | ~148 tok/s ModelFit est. |
| Nemotron Nano 9B v29B | FP16 | 19.4 GB | ~29 tok/s our est. |
| Qwen3.5 9B Instruct9B | Q8_0 | 12.0 GB | ~81 tok/s ModelFit est. |
| Qwen2.5 7B Instruct7B | Q4_K_M | 6.6 GB | ~135 tok/s ModelFit est. |
| Gemma 3 4B Instruct4B | Q8_0 | 5.0 GB | ~140 tok/s ModelFit est. |
| Qwen3.5 35B-A3B Instruct35B MoE | Q4_K_M | 21 GB | ~212 tok/s ModelFit est. |
| Ornith 1.0 35B35B | Q4_K_M | 23 GB | ~212 tok/s ModelFit est. |
| Nanbeige4.3 33B33.1B | Q4_K_M | 22 GB | no estimate |
| Laguna XS 2.133B | Q4_K_M | 22 GB | ~198 tok/s ModelFit est. |
| Qwen3 32B32B | Q4_K_M | 22 GB | ~36 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 32B32B | Q4_K_M | 21 GB | ~36 tok/s ModelFit est. |
| Olmo 3.1 32B Instruct32B | Q4_K_M | 21 GB | ~37 tok/s ModelFit est. |
| Cohere North Mini Code30B | Q4_K_M | 20 GB | no estimate |
| Nemotron 3.5 Lightning 30B-A3B30B MoE | IQ4_XS | 20 GB | ~272 tok/s our est. |
| GLM-4.7-Flash 30B-A3B30B MoE | Q4_K_M | 20 GB | ~156 tok/s ModelFit est. |
| Granite Switch 4.1 30B30B | Q4_K_M | 23 GB | no estimate |
| Muse Glimmer 30B29.8B | Q4_K_M | 18.3 GB | ~46 tok/s ModelFit est. |
| Granite 4.2 30B29.3B | Q4_K_M | 17.9 GB | ~40 tok/s ModelFit est. |
| AREX-2 27B27.4B | Q4_K_M | 18.6 GB | ~44 tok/s ModelFit est. |
| Gemma 2 27B Instruct27B | Q4_K_M | 23 GB | ~40 tok/s ModelFit est. |
| Gemma 3 27B Instruct27B | Q4_K_M | 23 GB | ~42 tok/s ModelFit est. |
| Qwen3.5 27B Instruct27B | Q4_K_M | 17.4 GB | ~46 tok/s ModelFit est. |
| Qwen3.6 27B27B | Q4_K_M | 19.4 GB | ~45 tok/s ModelFit est. |
| Jebadiah 27B27B | Q5_K_M | 21 GB | ~39 tok/s ModelFit est. |
| Mistral Small 3.124B | Q4_K_M | 16.4 GB | ~34 tok/s our est. |
| LFM2 24B-A2B Instruct24B MoE | Q4_K_M | 15.3 GB | ~225 tok/s ModelFit est. |
| Devstral Small 2 24B24B | Q4_K_M | 16.6 GB | ~47 tok/s ModelFit est. |
| Mistral Small 22B22B | Q4_K_M | 18.4 GB | ~54 tok/s ModelFit est. |
| Qwen2.5 14B Instruct14B | Q4_K_M | 12.3 GB | ~74 tok/s ModelFit est. |
| Phi-3 Medium 14B14B | Q4_K_M | 12.3 GB | ~47 tok/s our est. |
| Phi-4 14B14B | Q8_0 | 15.9 GB | ~46 tok/s ModelFit est. |
| Qwen2.5 Coder 14B14B | Q4_K_M | 12.3 GB | ~74 tok/s ModelFit est. |
| Qwen3 14B14B | Q8_0 | 17.3 GB | ~46 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 14B14B | Q8_0 | 16.0 GB | ~46 tok/s ModelFit est. |
| Ministral 3 14B13.5B | Q4_K_M | 10.3 GB | ~74 tok/s ModelFit est. |
| Mellum2.1 12B-A2.5B Thinking12.1B MoE | Q4_K_M | 9.3 GB | ~308 tok/s our est. |
| Mistral Nemo 12B12B | Q8_0 | 13.4 GB | ~55 tok/s ModelFit est. |
| Gemma 3 12B Instruct12B | Q4_K_M | 10.7 GB | ~86 tok/s ModelFit est. |
| Gemma 4 12B12B | Q8_0 | 14.1 GB | ~54 tok/s ModelFit est. |
| GLM-4-9B-Chat9.4B | Q8_0 | 11.2 GB | ~73 tok/s ModelFit est. |
| Gemma 2 9B Instruct9B | Q4_K_M | 8.2 GB | ~93 tok/s ModelFit est. |
| Ornith 1.0 9B9B | Q4_K_M | 6.7 GB | ~124 tok/s ModelFit est. |
| MiMo-V2.6-Distill-Qwen-9B9B | Q4_K_M | 6.9 GB | ~121 tok/s ModelFit est. |
| Jebadiah 9B9B | Q8_0 | 11.0 GB | ~79 tok/s ModelFit est. |
| Granite 4.2 8B8.8B | Q4_K_M | 6.1 GB | ~112 tok/s ModelFit est. |
| Granite Switch 4.1 8B8.8B | Q4_K_M | 7.6 GB | ~94 tok/s ModelFit est. |
| MiniCPM-V 4.5 8B8.7B | Q4_K_M | 6.8 GB | ~121 tok/s ModelFit est. |
| Ministral 3 8B8.4B | Q4_K_M | 7.1 GB | ~105 tok/s ModelFit est. |
| LFM2.5 8B-A1B8.3B MoE | Q4_K_M | 6.6 GB | ~270 tok/s ModelFit est. |
| Llama 3.1 8B Instruct8B | Q8_0 | 9.2 GB | ~80 tok/s ModelFit est. |
| Qwen3 8B8B | Q8_0 | 9.3 GB | ~78 tok/s ModelFit est. |
| Granite 4.1 8B Instruct8B | Q4_K_M | 6.6 GB | ~108 tok/s ModelFit est. |
| Mistral 7B Instruct7B | Q8_0 | 8.4 GB | ~84 tok/s ModelFit est. |
| Qwen2.5 Coder 7B7B | Q4_K_M | 6.6 GB | ~135 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 7B7B | Q8_0 | 8.7 GB | ~87 tok/s ModelFit est. |
| Gemma 4 E4B4.5B | Q8_0 | 8.7 GB | ~125 tok/s ModelFit est. |
| Qwen3.5 4B Instruct4B | Q8_0 | 5.4 GB | ~134 tok/s ModelFit est. |
| NVIDIA Nemotron 3.5 Bolt E4B4B | Q4_K_M | 9.1 GB | ~152 tok/s ModelFit est. |
| Phi-3 Mini 3.8B3.8B | Q4_K_M | 4.3 GB | ~161 tok/s our est. |
| Phi-4 Mini 3.8B3.8B | Q8_0 | 4.9 GB | ~133 tok/s ModelFit est. |
| Granite 4.2 3B3.7B | Q4_K_M | 3.2 GB | ~213 tok/s ModelFit est. |
| Ministral 3 3B3.4B | Q4_K_M | 4.1 GB | ~169 tok/s ModelFit est. |
| Qwen2.5 3B Instruct3B | Q4_K_M | 3.6 GB | ~235 tok/s ModelFit est. |
| Llama 3.2 3B Instruct3B | Q4_K_M | 3.6 GB | ~209 tok/s ModelFit est. |
| Granite 4.1 3B Instruct3B | Q4_K_M | 3.0 GB | ~212 tok/s ModelFit est. |
| Gemma 4 E2B2.3B | Q8_0 | 5.7 GB | ~235 tok/s ModelFit est. |
| Gemma 2 2B Instruct2B | Q4_K_M | 2.8 GB | ~230 tok/s ModelFit est. |
| Qwen3.5 2B Instruct2B | Q4_K_M | 2.8 GB | ~237 tok/s ModelFit est. |
| LFM3 1.7B1.73B | Q4_K_M | 2.1 GB | ~326 tok/s ModelFit est. |
| Qwen2.5 1.5B Instruct1.5B | Q4_K_M | 2.5 GB | ~333 tok/s ModelFit est. |
| Llama 3.2 1B Instruct1B | Q4_K_M | 2.0 GB | ~357 tok/s ModelFit est. |
| Gemma 3 1B Instruct1B | Q8_0 | 2.0 GB | ~334 tok/s ModelFit est. |
| Qwen3.5 0.8B Instruct0.8B | Q4_K_M | 1.8 GB | ~371 tok/s ModelFit est. |
| Qwen2.5 0.5B Instruct0.5B | Q4_K_M | 1.8 GB | ~461 tok/s ModelFit est. |
| SmolLM2 360M0.36B | Q4_K_M | 1.5 GB | ~365 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
Sage-A1.5 (23 GB), Qwen3.6-35B-A3B (24 GB), Qwen3 30B (24 GB), Flint 40B-A2.5B (24 GB), Poolside Laguna XS.2 (25 GB), NVIDIA Nemotron Cascade 2 30B-A3B (26 GB), Mixtral 8x7B Instruct (32 GB), Llama 3.3 70B (44 GB), Llama 3.1 70B Instruct (44 GB), DeepSeek-R1 Distill Llama 70B (44 GB), Kolibri 1 (46 GB), Qwen3-Next 80B-A3B (53 GB) and more.
Questions
What is the best AI model for the RTX 3090 (24 GB)?
Gemma 4 31B at Q4_K_M: the largest model on our shortlist of current models that runs at 4-bit or better at a usable speed (about 37 tok/s, ModelFit est.).
How much memory can a model use on the RTX 3090 (24 GB)?
About 23 GB of the 24 GB.
How fast is the RTX 3090 (24 GB) for local LLMs?
Decode speed is limited by memory bandwidth: 936 GB/s. A model that reads 10 GB per token runs at under 94 tokens per second.