Can I Run Devstral 2 22B on NVIDIA GeForce RTX 4060 Ti 16GB?
作者： Jakub Rusinowski · 最后更新： 2026年9月19日
Yes. Devstral 2 22B needs 13.3 GB at Q4_K_M and the NVIDIA GeForce RTX 4060 Ti 16GB has 16 GB, leaving about 2.7 GB of headroom, at roughly 18 tok/s (estimated) with room for up to 4K of context.
See what else this hardware can run →
The numbers
| Model | Devstral 2 22B |
| Parameters | 22B |
| Quantization | Q4_K_M |
| VRAM needed | 13.3 GB |
| NVIDIA GeForce RTX 4060 Ti 16GB VRAM | 16 GB |
| Verdict | Runs |
| Max context | 4K |
| Estimated speed | ~18 tok/s |
Devstral 2 22B on the NVIDIA GeForce RTX 4060 Ti 16GB: VRAM by quantization
| Quant | VRAM needed | Fits 16 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 45.6 GB | ✗ No | — | — |
| Q8_0 | 25 GB | ✗ No | — | — |
| Q6_K | 19.6 GB | ✗ No | — | — |
| Q5_K_M | 17.2 GB | ✗ No | — | — |
| Q4_K_M | 14.9 GB | ✓ Yes | 8K | — |
| Q3_K_M | 11 GB | ✓ Yes | 16K | — |
| Q2_K | 8.8 GB | ✓ Yes | 32K | — |
Assumes a 4K-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 16 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 4060 Ti 16GB: 8K 15.7 GB · 32K 20.5 GB ✗ · 125K 39.2 GB ✗. Past 32K it no longer fits 16 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? Devstral 2 22B on 16 GB of system RAM, CPU only: runs, but it is tight.
Running Devstral 2 22B on this card:
At 2 hrs/day, buying (~$499) beats renting at $0.34/hr after about 2.0 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.
Other Devstral sizes on the NVIDIA GeForce RTX 4060 Ti 16GB
- Devstral-2 123B — does not fit (74.3 GB)
- Devstral Small 2505 24B — runs (14.5 GB)
- Devstral Small 2 24B — runs at a lower quant (14.5 GB)
Devstral 2 22B on nearby hardware
- Intel Arc B580 (12 GB) — runs at a lower quant
- AMD Radeon RX 7900 XT (20 GB) — runs
All Devstral sizes on the NVIDIA GeForce RTX 4060 Ti 16GB | Devstral 2 22B model page | NVIDIA GeForce RTX 4060 Ti 16GB GPU page | Check your hardware