Can I Run Mistral Small 3.1 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Written by Jakub Rusinowski · Last updated March 17, 2025
Yes
Yes — Mistral Small 3.1 24B at Q6_K needs about 21.5 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) (~2.5 GB spare), at ~34.8 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: high · Recommended quantization: Q6_K · Estimated speed: ~34.8 tok/s
See what else this hardware can run →
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model
| Usable memory for models | 24 GB |
| Memory bandwidth | 1008 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
Mistral Small 3.1 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization
| Quant | Memory needed | Fits 24 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 49.3 GB | ✗ No | — | — | 47.2 GB |
| Q8_0 | 27.2 GB | ✗ No | — | — | 25.1 GB |
| Q6_K | 21.5 GB | ✓ Yes | 16K | ~34.8 tok/s | 19.4 GB |
| Q5_K_M | 18.9 GB | ✓ Yes | 32K | ~39.6 tok/s | 16.7 GB |
| Q4_K_M | 16.4 GB | ✓ Yes | 32K | ~45.5 tok/s | 14.2 GB |
| Q3_K_M | 12.2 GB | ✓ Yes | 64K | ~60.8 tok/s | 10.1 GB |
| Q2_K | 9.9 GB | ✓ Yes | 64K | ~74.6 tok/s | 7.8 GB |
RTX 4090 desktop limitations
- 24 GB is the sweet spot for 27–32B models at Q4; 70B needs offload or a second card.
Recommended setup
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 24 GB of VRAM on the NVIDIA GeForce RTX 4090 at 1008 GB/s.
- 64 GB of system RAM available for CPU offload when a model exceeds VRAM.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run Mistral Small 3.1 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Yes — Mistral Small 3.1 24B at Q6_K needs about 21.5 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) (~2.5 GB spare), at ~34.8 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of Mistral Small 3.1 should I use on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Q6_K — it needs about 21.5 GB of the 24 GB available, downloads as roughly 19.4 GB, and runs at an estimated 34.8 tokens/sec with up to 16K of context.
What limits Mistral Small 3.1 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Computers
Other Models on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Mistral Small 3.2 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Nemotron 3 Nano Omni on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Nemotron Cascade 2 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Nex-N2 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Nex-N2.5 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
Mistral Small 3.1 on GPUs
- Mistral Small 3.1 on NVIDIA GeForce RTX 5090
- Mistral Small 3.1 on NVIDIA GeForce RTX 5080
- Mistral Small 3.1 on NVIDIA GeForce RTX 5070 Ti
- Mistral Small 3.1 on NVIDIA GeForce RTX 5070
What This Model Is Good At
Model & Tools
← Can I Run It? | Mistral Small 3.1 model page | Check your hardware