Ministral 8B Instruct
Mistral 8B with sliding-window attention and 128k context. Research license — Mistral 7B v0.3 is the commercial alternative.
Overview
Mistral 8B with sliding-window attention and 128k context. Research license — Mistral 7B v0.3 is the commercial alternative.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- 128k context
- Sliding-window attention
Weaknesses
- Research license
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 5.0 GB | 8 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Ministral 8B Instruct.
Frequently asked
What's the minimum VRAM to run Ministral 8B Instruct?
Can I use Ministral 8B Instruct commercially?
What's the context length of Ministral 8B Instruct?
Source: huggingface.co/mistralai/Ministral-8B-Instruct-2410
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Ministral 8B Instruct runs on your specific hardware before committing money.