Ministral 3 3B Instruct 2512 is an open-source language model by mistralai. Features: 3b LLM, VRAM: 4.7GB, Context: 256K, License: MNPL-0.1, Instruction-Based.
Arxiv:2601.08584 Ar Base model:mistralai/ministral... Base model:quantized:mistralai... De En Es Fp8 Fr Instruct It Ja Ko Mistral-common Mistral3 Nl Pt Region:us Safetensors Vllm Zh
Model Card on HF 🤗: https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512
Ministral 3 3B Instruct 2512 Parameters and Internals
| LLM Name | Ministral 3 3B Instruct 2512 |
| Repository 🤗 | https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 4.7 GB |
| Updated | 2026-03-27 |
| Maintainer | mistralai |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en fr es de it pt nl zh ja ko ar |
| Model Architecture | MambaSSM |
| License | MNPL-0.1 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
Best Alternatives to Ministral 3 3B Instruct 2512
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...3.2 3B Instruct QLORA INT4 EO8 | 0K / GB | 191 | 69 |
| ...3B Instruct SpinQuant INT4 EO8 | 0K / GB | 86 | 37 |
Note: green Score (e.g. "73.2") means that the model is better than mistralai/Ministral-3-3B-Instruct-2512 .
Rank the Ministral 3 3B Instruct 2512 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51648 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b