Can I Run Mistral Small 3.2 on NVIDIA GeForce RTX 3090?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 6 września 2026
Yes, comfortably — Mistral Small 3.2 24B at Q4_K_M needs 16.7 GB at 8K context (14.2 GB weights + 2.5 GB KV cache/overhead), leaving ~7.3 GB of the NVIDIA GeForce RTX 3090's 24 GB, at ~36 tok/s (est.), with room for up to 32K context.
See what else this hardware can run →
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
NVIDIA GeForce RTX 3090 Specs
| VRAM | 24 GB |
| Memory Bandwidth | 936 GB/s |
Mistral Small 3.2 24B on the NVIDIA GeForce RTX 3090: VRAM by quantization
| Quant | VRAM needed | Fits 24 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 49.6 GB | ✗ No | — | — |
| Q8_0 | 27.5 GB | ✗ No | — | — |
| Q6_K | 21.8 GB | ✓ Yes | 16K | — |
| Q5_K_M | 19.2 GB | ✓ Yes | 16K | — |
| Q4_K_M | 16.7 GB | ✓ Yes | 32K | — |
| Q3_K_M | 12.5 GB | ✓ Yes | 32K | — |
| Q2_K | 10.2 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 24 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA GeForce RTX 3090: 8K 16.7 GB · 32K 21.6 GB · 128K 41.4 GB ✗. Past 128K it no longer fits 24 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Mistral Small 3.2 24B on 16 GB of system RAM, CPU only: runs, but it is tight.
Mistral Small 3.2 Sizes That Fit the NVIDIA GeForce RTX 3090 (at 8K context)
| Mistral Small 3.2 24B | Q4_K_M · 16.7 GB at 8K context · ~36 tok/s (est.) |
At 2 hrs/day, buying (~$1,499) beats renting at $0.34/hr after about 6.1 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the NVIDIA GeForce RTX 3090 enough to run Mistral Small 3.2 locally?
Yes, comfortably — Mistral Small 3.2 24B at Q4_K_M needs 16.7 GB at 8K context (14.2 GB weights + 2.5 GB KV cache/overhead), leaving ~7.3 GB of the NVIDIA GeForce RTX 3090's 24 GB, at ~36 tok/s (est.), with room for up to 32K context.
What's the best Mistral Small 3.2 size for the NVIDIA GeForce RTX 3090?
Mistral Small 3.2 24B at Q4_K_M quantization needs 16.7 GB at 8K context (14.2 GB weights + 2.5 GB KV cache/overhead), estimated ~36 tokens/sec, up to 32K context.
Mistral Small 3.2 on Other GPUs
- Mistral Small 3.2 on NVIDIA GeForce RTX 4090
- Mistral Small 3.2 on AMD Radeon RX 7900 XTX
- Mistral Small 3.2 on Apple M4 Pro
- Mistral Small 3.2 on Apple M3
- Mistral Small 3.2 on Apple M2
Popular Models on the NVIDIA GeForce RTX 3090
- DeepSeek R1 on NVIDIA GeForce RTX 3090
- Qwen 3 on NVIDIA GeForce RTX 3090
- Qwen 2.5 Family on NVIDIA GeForce RTX 3090
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | Mistral Small 3.2 Model Page | NVIDIA GeForce RTX 3090 GPU Page | VRAM calculator | Check Your Hardware