Which AI models run on a NVIDIA RTX 5090?
The NVIDIA RTX 5090 has 32 GB of VRAM. Here are the popular AI models it can run locally (4,096-token context, ~32.0 GB system RAM assumed), ranked by popularity.
See also: Best GPU for running local LLMs.
The NVIDIA RTX 5090 comes with 32 GB of VRAM. Among the popular GGUF models we track, it can run 37 of them entirely in VRAM — including Qwen3-Coder-30B-A3B-Instruct-GGUF, gpt-oss-20b-GGUF, Qwen-AgentWorld-35B-A3B-GGUF.
With 32 GB you can typically run a 30–32B model at high quality, or a 70B at low bit rates. Which quantization is best depends on the exact model and your context length. For a full shortlist, see the best LLM for 32 GB of VRAM.
Larger models such as Laguna-S-2.1-GGUF still run on a NVIDIA RTX 5090 but require offloading part of the model to system RAM, which lowers speed. Models that exceed both VRAM and RAM are not listed.
37 fit fully in VRAM · 1 run with offload
| Model | Size | Quant. | Quality | Memory | Speed~ | Verdict |
|---|---|---|---|---|---|---|
| unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF | 30.53B | Q8_0 | Excellent |
31.43 GB
|
13.2 t/s | Fits in VRAM |
| unsloth/gpt-oss-20b-GGUF | 20.91B | F16 | Very good |
13.74 GB
|
31.1 t/s | Fits in VRAM |
| unsloth/Qwen-AgentWorld-35B-A3B-GGUF | 34.66B | Q6_K_XL | Excellent |
30.53 GB
|
13.5 t/s | Fits in VRAM |
| MaziyarPanahi/Qwen3-4B-GGUF | 4.02B | GGUF | Excellent |
8.86 GB
|
53.3 t/s | Fits in VRAM |
| bartowski/Meta-Llama-3.1-8B-Instruct-GGUF | 8.03B | F32 | Excellent |
31.2 GB
|
13.4 t/s | Fits in VRAM |
| janhq/Jan-v3.5-4B-gguf | 4.41B | GGUF | Excellent |
9.59 GB
|
48.6 t/s | Fits in VRAM |
| Qwen/Qwen3-8B-GGUF | 8.19B | Q8_0 | Excellent |
9.47 GB
|
49.3 t/s | Fits in VRAM |
| MaziyarPanahi/Qwen3-0.6B-GGUF | 0.75B | GGUF | Excellent |
2.64 GB
|
284.6 t/s | Fits in VRAM |
| MaziyarPanahi/Qwen3-14B-GGUF | 14.77B | GGUF | Excellent |
28.94 GB
|
14.5 t/s | Fits in VRAM |
| MaziyarPanahi/Qwen3-1.7B-GGUF | 2.03B | GGUF | Excellent |
5.03 GB
|
105.5 t/s | Fits in VRAM |
| MaziyarPanahi/Qwen3-32B-GGUF | 32.76B | Q6_K | Excellent |
26.84 GB
|
16.0 t/s | Fits in VRAM |
| MaziyarPanahi/Qwen3-30B-A3B-GGUF | 30.53B | Q6_K | Excellent |
24.54 GB
|
17.1 t/s | Fits in VRAM |
| bartowski/Qwen2.5-7B-Instruct-GGUF | 7.62B | F16 | Excellent |
15.21 GB
|
28.2 t/s | Fits in VRAM |
| unsloth/Ornith-1.0-35B-GGUF | — | Q6_K_XL | Excellent |
30.53 GB
|
13.5 t/s | Fits in VRAM |
| Qwen/Qwen2.5-3B-Instruct-GGUF | 3.09B | GGUF | Excellent |
7.27 GB
|
63.2 t/s | Fits in VRAM |
| LiquidAI/LFM2.5-2.6B-GGUF | 2.7B | BF16 | Excellent |
5.89 GB
|
79.5 t/s | Fits in VRAM |
| LiquidAI/LFM2.5-1.2B-Instruct-GGUF | 1.17B | BF16 | Excellent |
3.03 GB
|
183.3 t/s | Fits in VRAM |
| bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF | 34.66B | Q6_K_L | Excellent |
29.1 GB
|
14.2 t/s | Fits in VRAM |
| Qwen/Qwen2.5-1.5B-Instruct-GGUF | 1.54B | GGUF | Excellent |
4.23 GB
|
120.6 t/s | Fits in VRAM |
| unsloth/Qwen3-Coder-Next-GGUF | 79.67B | IQ3_S | Low |
28.83 GB
|
14.5 t/s | Fits in VRAM |
| Qwen/Qwen2.5-Coder-7B-Instruct-GGUF | 7.62B | GGUF | Excellent |
15.21 GB
|
28.2 t/s | Fits in VRAM |
| MaziyarPanahi/Qwen3-4B-Instruct-2507-GGUF | 4.02B | GGUF | Excellent |
8.86 GB
|
53.3 t/s | Fits in VRAM |
| MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF | 8.03B | GGUF | Excellent |
16.24 GB
|
26.7 t/s | Fits in VRAM |
| MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF | 7.25B | GGUF | Excellent |
14.8 GB
|
29.6 t/s | Fits in VRAM |
| MaziyarPanahi/Mixtral-8x22B-v0.1-GGUF | 140.62B | IQ1_S | Very low |
29.28 GB
|
14.5 t/s | Fits in VRAM |
| Qwen/Qwen2.5-0.5B-Instruct-GGUF | 0.49B | GGUF | Excellent |
2.03 GB
|
339.1 t/s | Fits in VRAM |
| MaziyarPanahi/gemma-3-4b-it-GGUF | 4.3B | GGUF | Excellent |
8.38 GB
|
55.3 t/s | Fits in VRAM |
| MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF | 70.55B | Q3_K_S | Fair |
31.01 GB
|
13.9 t/s | Fits in VRAM |
| MaziyarPanahi/Phi-3.5-mini-instruct-GGUF | 3.82B | Q8_0 | Excellent |
6.08 GB
|
105.8 t/s | Fits in VRAM |
| lmstudio-community/Llama-3.2-3B-Instruct-GGUF | 3.21B | Q8_0 | Excellent |
4.29 GB
|
125.5 t/s | Fits in VRAM |
| MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF | 8.03B | GGUF | Excellent |
16.24 GB
|
26.7 t/s | Fits in VRAM |
| MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF | 23.57B | Q8_0 | Excellent |
24.76 GB
|
17.1 t/s | Fits in VRAM |
| MaziyarPanahi/Yi-1.5-6B-Chat-GGUF | 6.06B | Q6_K | Excellent |
5.68 GB
|
86.3 t/s | Fits in VRAM |
| MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF | 1.24B | GGUF | Excellent |
3.3 GB
|
173.2 t/s | Fits in VRAM |
| MaziyarPanahi/Mistral-Nemo-Instruct-2407-GGUF | 12.25B | GGUF | Excellent |
24.25 GB
|
17.5 t/s | Fits in VRAM |
| unsloth/GLM-4.7-Flash-GGUF | 31.22B | Q8_0 | Excellent |
30.66 GB
|
13.5 t/s | Fits in VRAM |
| MaziyarPanahi/WizardLM-2-7B-GGUF | 7.24B | GGUF | Excellent |
14.74 GB
|
29.7 t/s | Fits in VRAM |
| unsloth/Laguna-S-2.1-GGUF | 117.56B | IQ4_NL | Fair |
55.7 GB
|
0.9 t/s | Offload |
"Fits in VRAM" = fast, fully on GPU. "Offload" = part on system RAM, slower. Speed is a rough estimate.
Frequently asked questions
How much VRAM does the NVIDIA RTX 5090 have?
The NVIDIA RTX 5090 has 32 GB of VRAM, which determines how large a model it can run entirely on the GPU.
What is the best LLM to run on a NVIDIA RTX 5090?
Among popular models, unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF runs well on a NVIDIA RTX 5090 using the Q8_0 quantization (about 31.43 GB). With 32 GB you can generally run a 30–32B model at high quality, or a 70B at low bit rates. Larger models trade speed for capability via RAM offloading. See the best LLM for 32 GB of VRAM.
Can a NVIDIA RTX 5090 run a 7–8B model?
Yes. A 7–8B model like Meta-Llama-3.1-8B-Instruct-GGUF fits entirely in the 32 GB of a NVIDIA RTX 5090 (F32).
Can a NVIDIA RTX 5090 run a 13–14B model?
Yes. A 13–14B model like Qwen3-14B-GGUF fits entirely in the 32 GB of a NVIDIA RTX 5090 (GGUF).
Can a NVIDIA RTX 5090 run a 70B model?
Yes. A 70B model like Qwen3-Coder-Next-GGUF fits entirely in the 32 GB of a NVIDIA RTX 5090 (IQ3_S).