Models · family
Mistral
7 MLX aliases · Mistral's general + code lines — Ministral / Mistral / Mistral-Small-4 / Devstral.
The Mistral line on rapid-mlx covers Mistral's general-purpose 3B and 24B chat models, the 119B Mistral-Small-4, and the Devstral code-tuned 24B variants (V1 + V2). All use the hermes tool envelope so OpenAI-compatible clients work without per-model config.
- family
- Mistral
- aliases
- 7
- lines
- 2
- install
- rapid-mlx serve <alias>
- OpenAI base URL
- http://localhost:8000/v1
Lines in this family
Mistral (chat) · 5 aliases
Ministral 3B and Mistral 24B — general-purpose chat models. Ministral 3B is excellent as a draft model for Mistral 24B speculative decoding.
parser: hermes
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| ministral-3b-4bit | mlx-community/Ministral-3-3B-Instruct-2512-4bit | hermes | — | spec |
| mistral-24b-4bit | mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit | hermes | — | spec |
| mistral-small-4-119b | mlx-community/Mistral-Small-4-119B-2603-4bit | hermes | — | spec |
| mistral-small-4-119b-4bit | mlx-community/Mistral-Small-4-119B-2603-4bit | hermes | — | spec |
| mistral-small-4-119b-8bit | mlx-community/Mistral-Small-4-119B-2603-8bit | hermes | — | spec |
Notes & caveats
- Ministral 3B is excellent as a draft model for Mistral 24B speculative decoding.
Devstral · 2 aliases
Code-tuned Mistral 24B in two generations — V1 and V2. Devstral V2 is strictly better than V1 on SWE-Bench; we keep V1 in the registry for reproducibility.
parser: hermes
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| devstral-24b-4bit | mlx-community/Devstral-Small-2507-4bit | hermes | — | spec |
| devstral-v2-24b-4bit | mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit | hermes | — | spec |
Notes & caveats
- Devstral V2 is the recommended pick for code on a 32 GB+ Mac — strictly better than V1 on SWE-Bench.