作者： Jakub Rusinowski · 最后更新： 2026年7月10日
Mistral's dedicated code generation model, trained on a massive programming corpus covering 80+ programming languages. Excels at fill-in-the-middle (FIM) completion — the key technique powering IDE autocomplete. Integrates natively with VS Code via continue.dev and Cursor.
| Codestral 22B | Min 14 GB VRAM · Q4_K_M · 32,768 ctx · ollama run codestral:22b |
The cheapest GPU that runs Codestral locally (min 14 GB VRAM) is the AMD Radeon RX 9060 XT 16GB (16 GB).
Install Ollama then run: ollama run codestral:22b
Minimum VRAM: 14 GB. For best results use Q4_K_M quantization.
Codestral needs about 14 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Codestral 22B (14 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Codestral runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Codestral in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run codestral:22b. This downloads Codestral and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.