Can the GeForce RTX 5090 run Codestral 22B v0.1?
Fits comfortably at Q4_K_M.
Codestral 22B v0.1 is 22.2B parameters. At Q4_K_M the weights are about 12.4 GiB; with the 1.5 GiB runtime reserve that is 13.9 GiB against the card's 32GB, leaving about 18.1 GiB for context.
All three quants
32GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 12.4 GiB | 13.9 GiB | Fits comfortably | 18.1 GiB |
| Q8_0near-lossless | 21.9 GiB | 23.4 GiB | Fits comfortably | 8.6 GiB |
| FP16full weights | 41.4 GiB | 42.9 GiB | Only with CPU offload | short 10.9 GiB |
Verdict rules: fits comfortably when weights plus reserve sit within 85% of VRAM; tight when they fit with little left for context; CPU offload when they exceed VRAM by up to 2x (runs, slowly, with layers in system RAM); no beyond that. The KV cache per token depends on the model's architecture and is not modelled here.
Good match. Get the card.
The GeForce RTX 5090 clears Codestral 22B v0.1 at Q4_K_M and at Q8_0. Live listings below; this page was rebuilt 2026-08-23.
Amazon links may earn us a commission. Prices move daily; the links open live listings.
About the model
Codestral 22B v0.1 by Mistral AI: 32,768-token native context, text, released 2024 under the Mistral AI Non-Production License. Model card →