Can I Run Devstral on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Written by Jakub Rusinowski · Last updated September 11, 2026
Yes, but it is tight
Yes, but it is tight — Devstral Small 2505 24B at Q6_K needs about 21.8 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~2.2 GB before the runtime starts swapping. Expect ~34.3 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~34.3 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 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 |
Devstral 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 | 50.1 GB | ✗ No | — | — | 48 GB |
| Q8_0 | 27.6 GB | ✗ No | — | — | 25.5 GB |
| Q6_K | 21.8 GB | ✓ Yes | 16K | ~34.3 tok/s | 19.7 GB |
| Q5_K_M | 19.2 GB | ✓ Yes | 32K | ~39 tok/s | 17 GB |
| Q4_K_M | 16.6 GB | ✓ Yes | 32K | ~44.8 tok/s | 14.5 GB |
| Q3_K_M | 12.4 GB | ✓ Yes | 64K | ~60 tok/s | 10.2 GB |
| Q2_K | 10 GB | ✓ Yes | 64K | ~73.7 tok/s | 7.9 GB |
Which Devstral sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Devstral-2 123B | 77.9 GB | ✗ Too large | — |
| Devstral Small 2505 24B | 16.6 GB | ✓ Fits | ~44.8 tok/s |
| Devstral Small 2 24B | 16.6 GB | ✓ Fits | ~44.8 tok/s |
| Devstral 2 22B | 15.7 GB | ✓ Fits | ~47.9 tok/s |
What to watch out for
- 1 larger variant of Devstral does not fit and would need CPU offload or different hardware.
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 Devstral on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Yes, but it is tight — Devstral Small 2505 24B at Q6_K needs about 21.8 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~2.2 GB before the runtime starts swapping. Expect ~34.3 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of Devstral should I use on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Q6_K — it needs about 21.8 GB of the 24 GB available, downloads as roughly 19.7 GB, and runs at an estimated 34.3 tokens/sec with up to 16K of context.
What limits Devstral 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)
- EXAONE 3.5 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Falcon 3 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Gemma 2 Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Gemma 3 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Gemma 3n on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
Devstral on GPUs
- Devstral on NVIDIA GeForce RTX 5090
- Devstral on NVIDIA GeForce RTX 5080
- Devstral on NVIDIA GeForce RTX 5070 Ti
- Devstral on NVIDIA GeForce RTX 5070