Can I Run Magistral Small on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?
Written by Jakub Rusinowski · Last updated September 6, 2026
Yes, but it is tight
Yes, but it is tight — Magistral Small 24B at Q6_K needs about 22.2 GB of the 24 GB usable on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1.8 GB before the runtime starts swapping. Expect ~31.8 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: low · Recommended quantization: Q6_K · Estimated speed: ~31.8 tok/s
Get a personalized upgrade path →
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 3090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model
| Usable memory for models | 24 GB |
| Memory bandwidth | 936 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
Magistral Small on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization
| Quant | Memory needed | Fits 24 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 50.5 GB | ✗ No | — | — | 48 GB |
| Q8_0 | 28 GB | ✗ No | — | — | 25.5 GB |
| Q6_K | 22.2 GB | ✓ Yes | 16K | ~31.8 tok/s | 19.7 GB |
| Q5_K_M | 19.5 GB | ✓ Yes | 16K | ~36.1 tok/s | 17 GB |
| Q4_K_M | 17 GB | ✓ Yes | 32K | ~41.5 tok/s | 14.5 GB |
| Q3_K_M | 12.7 GB | ✓ Yes | 32K | ~55.5 tok/s | 10.2 GB |
| Q2_K | 10.4 GB | ✓ Yes | 64K | ~68.1 tok/s | 7.9 GB |
What to watch out for
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
RTX 3090 desktop limitations
- The cheapest route to 24 GB of VRAM, and the standard used-market recommendation for local LLMs.
- Older architecture: no FP8 acceleration, and higher idle power than a current 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 3090 at 936 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 inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run Magistral Small on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?
Yes, but it is tight — Magistral Small 24B at Q6_K needs about 22.2 GB of the 24 GB usable on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1.8 GB before the runtime starts swapping. Expect ~31.8 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of Magistral Small should I use on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?
Q6_K — it needs about 22.2 GB of the 24 GB available, downloads as roughly 19.7 GB, and runs at an estimated 31.8 tokens/sec with up to 16K of context.
What limits Magistral Small on RTX 3090 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 3090 Desktop (24 GB VRAM, 64 GB RAM)
- MiniCPM-V on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- Ministral on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- Ministral 3 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- Mistral Family on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- Mistral Small 3.1 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
Magistral Small on GPUs
- Magistral Small on NVIDIA GeForce RTX 5090
- Magistral Small on NVIDIA GeForce RTX 5080
- Magistral Small on NVIDIA GeForce RTX 5070 Ti
- Magistral Small on NVIDIA GeForce RTX 5070
What This Model Is Good At
Model & Tools
← Can I Run It? | Magistral Small model page | Check your hardware