Mistral Small 4 119B 2603 OptiQ 2bit by mlx-community

 »  All LLMs  »  mlx-community  »  Mistral Small 4 119B 2603 OptiQ 2bit   URL Share it on

Mistral Small 4 119B 2603 OptiQ 2bit is an open-source language model by mlx-community. Features: 119b LLM, VRAM: 45GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.33.

  2bit   4-bit   Ar Base model:mlx-community/mistr... Base model:quantized:mlx-commu...   Bn   Conversational   De   En   Es   Fa   Fr   Hi   Id   It   Ja   Ko   Mistral3   Mlx   Ms   Ne   Optiq   Pl   Pt   Quantized   Region:us   Ro   Ru   Safetensors   Sharded   Sr   Sv   Tensorflow   Tr   Uk   Vi   Zh

Mistral Small 4 119B 2603 OptiQ 2bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral Small 4 119B 2603 OptiQ 2bit (mlx-community/Mistral-Small-4-119B-2603-OptiQ-2bit)

Mistral Small 4 119B 2603 OptiQ 2bit Parameters and Internals

LLM NameMistral Small 4 119B 2603 OptiQ 2bit
Repository 🤗https://huggingface.co/mlx-community/Mistral-Small-4-119B-2603-OptiQ-2bit 
Base Model(s)  Mistral Small 4 119B 2603 Bf16   mlx-community/Mistral-Small-4-119B-2603-bf16
Model Size119b
Required VRAM45 GB
Updated2026-07-25
Maintainermlx-community
Model Typemistral3
Model Files  5.2 GB: 1-of-9   5.2 GB: 2-of-9   5.2 GB: 3-of-9   5.2 GB: 4-of-9   5.2 GB: 5-of-9   5.2 GB: 6-of-9   5.1 GB: 7-of-9   5.3 GB: 8-of-9   3.4 GB: 9-of-9
Supported Languagesen fr de es pt it ja ko ru zh ar fa id ms ne pl ro sr sv tr uk vi hi bn
Quantization Type2bit
Model ArchitectureMistral3ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.3.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<pad>

Best Alternatives to Mistral Small 4 119B 2603 OptiQ 2bit

Best Alternatives
Context / RAM
Downloads
Likes
Mistral Small 4 119B 2603 Bf160K / 191.9 GB1030

Rank the Mistral Small 4 119B 2603 OptiQ 2bit 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 55396 in total.

Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a