LLM EXPLORER 61,060 MODELS INDEXED

Ministral 8B Instruct 2410 by mistralai

By mistralai · 299686 downloads
HF Repo ↗ Copy URL

Ministral 8B Instruct 2410 is an open-source language model by mistralai. Features: 8b LLM, VRAM: 16.1GB, License: MNPL-0.1, Instruction-Based, LLM Explorer Score: 0.45, ELO: 1237.

  De   En   Es   Eval-results   Fr   Instruct   It   Ja   Ko   Mistral   Mistral-common   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Vllm   Zh
Model Card on HF 🤗: https://huggingface.co/mistralai/Ministral-8B-Instruct-2410 

Ministral 8B Instruct 2410 Benchmarks

LMSys ELO 1237 vs 1272 (so35) -2.8%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Ministral 8B Instruct 2410 Parameters and Internals

Model Type 
instruct fine-tuned model
Use Cases 
Areas:
local intelligence, on-device computing, at-the-edge use cases
Applications:
research
Primary Use Cases:
non-commercial research purposes
Limitations:
Only for non-commercial research purposes
Additional Notes 
Trained with a 128k context window utilizing interleaved sliding-window attention.
Supported Languages 
en (English), fr (French), de (German), es (Spanish), it (Italian), pt (Portuguese), zh (Chinese), ja (Japanese), ru (Russian), ko (Korean)
Training Details 
Context Length:
128000
Model Architecture:
Dense Transformer
Input Output 
Input Format:
V3-Tekken tokenizer format
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use Mistral Inference or vLLM for optimized performance.
Release Notes 
Version:
8B-Instruct-2410
Date:
2023-10
Notes:
Release of Ministral-8B-Instruct-2410 under Mistral Research License
LLM NameMinistral 8B Instruct 2410
Repository 🤗https://huggingface.co/mistralai/Ministral-8B-Instruct-2410 
Model Size8b
Required VRAM16.1 GB
Updated2026-06-30
Maintainermistralai
Instruction-BasedYes
Model Files  16.0 GB   5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.1 GB: 4-of-4
Supported Languagesen fr de es it pt zh ja ru ko
Model ArchitectureMambaSSM
LicenseMNPL-0.1

Quantized Models of the Ministral 8B Instruct 2410

Model
Likes
Downloads
VRAM
...inistral 8B Instruct 2410 GGUF31313 GB

Best Alternatives to Ministral 8B Instruct 2410

Best Alternatives
Context / RAM
Downloads
Likes
Ministral 3 8B Instruct 2512256K / 10.4 GB123761189
...istral 3 8B Instruct 2512 BF16256K / 17.8 GB1401923
...8B Instruct 2512 BF16 SOM MPOA256K / 17.8 GB160
Ministral 8B Instruct 2410 HF0K / 16.1 GB70