NVIDIA graphics card
What AI models can the NVIDIA GeForce RTX 5090 32 GB run?
At 4-bit quantization with an 8K-token conversation, 61 of the 146 open-weight models in our directory fit entirely in the NVIDIA GeForce RTX 5090 32 GB's 32 GB of video memory (about 31 GB usable), up to Skyfall 36B V2. With 32 GB of dual-channel DDR5-5600, 11 more run partly from system RAM, more slowly. Among models of 7B parameters or more, Laguna XS 2.1 (free) is the fastest, at an estimated 371 to 480 tokens per second.
| Model | Parameters | Memory needed | Estimated speed |
|---|---|---|---|
| Runs entirely in fast memory (61) | |||
| Skyfall 36B V2 Thedrummer | 36.9B | 25 GB 22 GB + 2.1 GB cache | 42–54 tokens/s Fast |
| Qwen3.5 35B-A3B Alibaba (Qwen) | 36.0B 4.7B active | 23 GB 22 GB + 0.2 GB cache | 246–318 tokens/s Fast |
| Qwen3.6 35B-A3B Alibaba (Qwen) | 36.0B 4.7B active | 23 GB 22 GB + 0.2 GB cache | 246–318 tokens/s Fast |
| Nex-N2.5-Mini NEX AGI | 35.1B 3.9B active | 22 GB 21 GB + 0.2 GB cache | 280–363 tokens/s Fast |
| Laguna XS 2.1 (free) Poolside | 33.4B 2.2B active | 21 GB 20 GB + 0.4 GB cache | 371–480 tokens/s Fast |
| Qwen3 VL 32B Instruct Alibaba (Qwen) | 33.4B | 23 GB 20 GB + 2.1 GB cache | 46–59 tokens/s Fast |
| Qwen2.5 Coder 32B Instruct Alibaba (Qwen) | 32.8B | 23 GB 20 GB + 2.1 GB cache | 46–60 tokens/s Fast |
| Qwen3 32B Alibaba (Qwen) | 32.8B | 23 GB 20 GB + 2.1 GB cache | 46–60 tokens/s Fast |
| Nemotron 3 Nano 30B A3B NVIDIA | 31.6B | 20 GB 19 GB + 0.1 GB cache | Speed not estimated for this architecture |
| Nemotron 3.5 Lightning 30B A3B NVIDIA | 31.6B | 20 GB 19 GB + 0.4 GB cache | Speed not estimated for this architecture |
| Gemma 4 31B IT Google DeepMind | 31.3B | 22 GB 19 GB + 2.2 GB cache | 48–62 tokens/s Fast |
| GLM-4.7-Flash Zhipu AI (Z.ai) | 31.2B 5.2B active | 20 GB 19 GB + 0.4 GB cache | 224–290 tokens/s Fast |
| Qwen3 VL 30B A3B Instruct Alibaba (Qwen) | 31.1B 3.9B active | 20 GB 19 GB + 0.8 GB cache | 258–334 tokens/s Fast |
| Qwen3 VL 30B A3B Thinking Alibaba (Qwen) | 31.1B 3.9B active | 20 GB 19 GB + 0.8 GB cache | 258–334 tokens/s Fast |
| Qwen3-Coder 30B-A3B Instruct Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 281–364 tokens/s Fast |
| Qwen3 30B A3B Instruct 2507 Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 281–364 tokens/s Fast |
| Qwen3 30B A3B Thinking 2507 Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 281–364 tokens/s Fast |
| Qwen3 30B A3B Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 281–364 tokens/s Fast |
| Hy-MT2-30B-A3B Tencent (Hunyuan) | 30.1B 3.5B active | 20 GB 18 GB + 0.8 GB cache | 277–358 tokens/s Fast |
| Muse Glimmer 30B Meta | 29.8B | 19 GB 18 GB + 0.2 GB cache | 53–68 tokens/s Fast |
| Qwen3.8 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 56–72 tokens/s Fast |
| Qwen3.5 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 56–72 tokens/s Fast |
| Qwen3.6 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 56–72 tokens/s Fast |
| Gemma 3 27B IT Google DeepMind | 27.4B | 17 GB weights only | Speed not estimated (architecture not public) |
| Gemma 2 27B Google DeepMind | 27.2B | 17 GB weights only | Speed not estimated (architecture not public) |
| Gemma 4 26B A4B IT Google DeepMind | 25.8B | 17 GB 16 GB + 0.5 GB cache | Speed not estimated for this architecture |
| Voxtral Small 24B 2507 Mistral AI | 24.3B | 17 GB 15 GB + 1.3 GB cache | 62–80 tokens/s Fast |
| Uncensored Cognitivecomputations | 24.0B | 17 GB 15 GB + 1.3 GB cache | 62–81 tokens/s Fast |
| Mistral Small 3.1 24B Instruct Mistral AI | 24.0B | 17 GB 15 GB + 1.3 GB cache | 62–81 tokens/s Fast |
| LFM2.5-24B-A2B Liquid | 24.0B | 16 GB 15 GB + 0.2 GB cache | Speed not estimated for this architecture |
| Mistral Small 3 Mistral AI | 23.6B | 16 GB 14 GB + 1.3 GB cache | 63–82 tokens/s Fast |
| Cydonia 24B V4.1 Thedrummer | 23.6B | 16 GB 14 GB + 1.3 GB cache | 63–82 tokens/s Fast |
| Cydonia 24B V4.1 Thedrummer | 23.6B | 16 GB 14 GB + 1.3 GB cache | 63–82 tokens/s Fast |
| Safety GPT OSS 20B OpenAI | 21.5B 4.8B active | 14 GB 13 GB + 0.2 GB cache | 243–315 tokens/s Fast |
| GPT OSS 20B OpenAI | 20.9B 4.2B active | 14 GB 13 GB + 0.2 GB cache | 266–344 tokens/s Fast |
| Reka Flash 3 Rekaai | 20.9B | 15 GB 13 GB + 1.1 GB cache | 71–92 tokens/s Fast |
| Qwen3 14B Alibaba (Qwen) | 14.8B | 11 GB 9.0 GB + 1.3 GB cache | 95–122 tokens/s Fast |
| Phi 4 Microsoft | 14.7B | 11 GB 8.9 GB + 1.7 GB cache | 94–121 tokens/s Fast |
| Ministral 3 14B Mistral AI | 13.9B | 11 GB 8.5 GB + 1.3 GB cache | 99–128 tokens/s Fast |
| Gemma 3 12B IT Google DeepMind | 12.2B | 8.2 GB weights only | Speed not estimated (architecture not public) |
| Llama Guard 4 12B Meta | 12.0B | 8.1 GB weights only | Speed not estimated (architecture not public) |
| Qwen3.5 9B Alibaba (Qwen) | 9.7B | 6.9 GB 5.9 GB + 0.3 GB cache | 142–184 tokens/s Fast |
| Moondream 3.1 Moondream | 9.3B | 6.4 GB weights only | Speed not estimated (architecture not public) |
| Moondream 3 Preview Moondream | 9.3B | 6.4 GB weights only | Speed not estimated (architecture not public) |
| Ministral 3 8B Mistral AI | 8.9B | 7.3 GB 5.4 GB + 1.1 GB cache | 143–185 tokens/s Fast |
| Granite 4.2 8B IBM | 8.8B | 7.5 GB 5.3 GB + 1.3 GB cache | 142–184 tokens/s Fast |
| Qwen3 VL 8B Instruct Alibaba (Qwen) | 8.8B | 7.3 GB 5.3 GB + 1.2 GB cache | 144–186 tokens/s Fast |
| Qwen3 VL 8B Thinking Alibaba (Qwen) | 8.8B | 7.3 GB 5.3 GB + 1.2 GB cache | 144–186 tokens/s Fast |
| UI-TARS 7B Bytedance | 8.3B | 6.3 GB 5.0 GB + 0.5 GB cache | 158–205 tokens/s Fast |
| Qwen3 8B Alibaba (Qwen) | 8.2B | 7.0 GB 5.0 GB + 1.2 GB cache | 151–196 tokens/s Fast |
| Llama 3.1 8B Instruct fp8 Meta | 8.0B | 5.7 GB weights only | Speed not estimated (architecture not public) |
| Hy-MT2-7B Tencent (Hunyuan) | 8.0B | 6.7 GB 4.9 GB + 1.1 GB cache | 155–201 tokens/s Fast |
| Qwen2.5 7B Instruct Alibaba (Qwen) | 7.6B | 5.9 GB 4.6 GB + 0.5 GB cache | 169–219 tokens/s Fast |
| Gemma 3 4B IT Google DeepMind | 4.3B | 3.4 GB weights only | Speed not estimated (architecture not public) |
| Nemotron 3.5 Content Safety (free) NVIDIA | 4.3B | 3.7 GB 2.6 GB + 0.3 GB cache | 259–335 tokens/s Fast |
| Ministral 3 3B Mistral AI | 3.8B | 4.0 GB 2.3 GB + 0.9 GB cache | 258–333 tokens/s Fast |
| Llama 3.2 3B Instruct Meta | 3.2B | 2.7 GB weights only | Speed not estimated (architecture not public) |
| Granite 4.0 Micro IBM | 3.2B | 2.8 GB 1.9 GB + 0.1 GB cache | 323–418 tokens/s Fast |
| Hy-MT2-1.8B Tencent (Hunyuan) | 2.0B | 2.6 GB 1.2 GB + 0.5 GB cache | 378–489 tokens/s Fast |
| Hy-MT2-1.8B Tencent (Hunyuan) | 2.0B | 2.6 GB 1.2 GB + 0.5 GB cache | 378–489 tokens/s Fast |
| Llama 3.2 1B Instruct Meta | 1.2B | 1.5 GB weights only | Speed not estimated (architecture not public) |
| Runs, partly from system RAM (slower) (11) | |||
| Qwen3-Next 80B-A3B Instruct Alibaba (Qwen) | 81.3B 5.5B active | 51 GB 49 GB + 0.8 GB cache | 56–76 tokens/s Fast, 20 GB in system RAM |
| Qwen3-Next 80B-A3B (Thinking) Alibaba (Qwen) | 81.3B 5.5B active | 51 GB 49 GB + 0.8 GB cache | 56–76 tokens/s Fast, 20 GB in system RAM |
| Hunyuan A13B Instruct Tencent (Hunyuan) | 80.4B | 51 GB 49 GB + 1.1 GB cache | 19 GB in system RAM; Speed not estimated for this architecture |
| Qwen3 Coder Next Alibaba (Qwen) | 79.7B 3.9B active | 50 GB 48 GB + 0.8 GB cache | 62–85 tokens/s Fast, 19 GB in system RAM |
| Qwen2.5-VL 72B Instruct Alibaba (Qwen) | 73.4B | 48 GB 45 GB + 2.7 GB cache | 1.8–2.4 tokens/s Too slow for chat, 17 GB in system RAM |
| Qwen2.5 72B Instruct Alibaba (Qwen) | 72.7B | 48 GB 44 GB + 2.7 GB cache | 1.8–2.5 tokens/s Too slow for chat, 16 GB in system RAM |
| Magnum v4 72B Anthracite ORG | 72.7B | 48 GB 44 GB + 2.7 GB cache | 1.8–2.5 tokens/s Too slow for chat, 16 GB in system RAM |
| Hermes 3 70B Instruct Nousresearch | 70.6B | 46 GB 43 GB + 2.7 GB cache | 2.0–2.7 tokens/s Too slow for chat, 15 GB in system RAM |
| Hermes 3 70B Instruct Nousresearch | 70.6B | 46 GB 43 GB + 2.7 GB cache | 2.0–2.7 tokens/s Too slow for chat, 15 GB in system RAM |
| Llama-3.3-70B-Instruct Meta | 70.6B | 44 GB weights only | 12 GB in system RAM; Speed not estimated (architecture not public) |
| Llama-3.1-70B-Instruct Meta | 70.6B | 44 GB weights only | 12 GB in system RAM; Speed not estimated (architecture not public) |
74 larger models do not fit. Change the quantization, conversation length or system RAM in the tool.
Compared with similar cards
- NVIDIA GeForce RTX 4090 24 GB: 24 GB, 60 models fit entirely (-1); about 22% slower on models that fit both (1008 vs 1792 GB/s).
- AMD Radeon AI PRO R9700 32 GB: same memory, so the same models fit; about 55% slower on models that fit both (640 vs 1792 GB/s, and AMD cards run llama.cpp less efficiently than NVIDIA's).
- Intel Arc Pro B70 32 GB: same memory, so the same models fit; about 67% slower on models that fit both (608 vs 1792 GB/s, and Intel cards run llama.cpp less efficiently than NVIDIA's).
Frequently asked questions
What is the largest AI model the NVIDIA GeForce RTX 5090 32 GB can run?
At 4-bit quantization with an 8K-token conversation, the largest model in our directory that fits entirely in its 32 GB of video memory is Skyfall 36B V2 (25 GB). With 32 GB of dual-channel DDR5-5600 for the overflow, larger models such as Qwen3-Next 80B-A3B Instruct also run, more slowly, partly from system RAM.
Can the NVIDIA GeForce RTX 5090 32 GB run GPT OSS 20B?
Yes. At 4-bit, GPT OSS 20B needs about 14 GB and fits entirely in the NVIDIA GeForce RTX 5090 32 GB's memory at an estimated 266 to 344 tokens per second.
Can the NVIDIA GeForce RTX 5090 32 GB run Qwen3 32B?
Yes. At 4-bit, Qwen3 32B needs about 23 GB and fits entirely in the NVIDIA GeForce RTX 5090 32 GB's memory at an estimated 46 to 60 tokens per second.
Can the NVIDIA GeForce RTX 5090 32 GB run OpenAI GPT 120B?
No. OpenAI GPT 120B needs about 72 GB at 4-bit, more than the NVIDIA GeForce RTX 5090 32 GB can hold even with 32 GB of dual-channel DDR5-5600 for overflow.
These are estimates, not measurements: memory from each model's parameter count and published architecture, speed from memory bandwidth, calibrated on the AIPCs test bench. Drivers, software and prompt length move real results. How the estimate works.