Model · Mistral AI · Text
Mistral Small 4
Mistral's hybrid open model that unifies instruct, reasoning, and coding in a single efficient line. It is the current small generalist flagship in Mistral's open lineup.
- Modality
- Text
- License
- Apache 2.0 (Open)
- Parameter size
- 119B total / 6.5B active
- Context window
- 256,000 tokens
- Released
- March 16, 2026
- Last verified
- October 28, 2026
- Runs locally
- Yes
- Also handles
- reasoning, code, vision
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 96 GB (128 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 80 GB (160 GB recommended) of video memory.
- No graphics card
- Not practical. Too slow without a graphics card or Apple Silicon.
Despite the name it is a 119B model: it needs a 96 GB or larger Mac (MLX and LM Studio builds exist) or an 80 GB graphics card.
Numbers are for: 4-bit build of the 119B model (about 65 GB). Our estimate from the model’s size — the maker publishes no figure.
Strengths
- Blends chat, reasoning, coding, and vision into one model
- 256k context window
- Open weights for self-hosted deployment
Weaknesses
- Heavier than earlier small open models despite the product name
- Less convenient for truly modest hardware than 7B-14B-class models
Try it
| Where | Type | Notes |
|---|---|---|
| Mistral La Plateforme | hosted-api | API key required |
| Mistral model card | weights | Open weights |
Used in solutions
Official sources
- Model card docs
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: estimate from 119B size at 4-bit; Mistral model card lists llama.cpp builds.
- — Verified current against Mistral's models overview (v26.03, still listed as active) and changelog. Licence corrected from "Open weights" to Apache 2.0 (as the overview states), which moves it under the Open filter.
- — Verified current against Mistral's models overview and model card; release date matches exactly. Now described as a hybrid model unifying instruct, reasoning and coding.
- — Added after verification of Mistral's current frontier multimodal lineup.
Esc