LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Magistral Small 2506 4bit DWQ by mlx-community

 »  All LLMs  »  mlx-community  »  Magistral Small 2506 4bit DWQ   URL Share it on

  32   

Magistral Small 2506 4bit DWQ is an open-source language model by mlx-community. Features: 23.6b LLM, VRAM: 13.3GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.2.

  4-bit   4bit   Ar Base model:mlx-community/magis... Base model:quantized:mlx-commu...   Bn   Conversational   De   En   Es   Fa   Fr   Hi   Id   It   Ja   Ko   Mistral   Mlx   Ms   Ne   Pl   Pt   Quantized   Region:us   Ro   Ru   Safetensors   Sharded   Sr   Sv   Tensorflow   Tr   Uk   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/Magistral-Small-2506-4bit-DWQ 

Magistral Small 2506 4bit DWQ Benchmarks

LLME Score: 0.19535
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magistral Small 2506 4bit DWQ (mlx-community/Magistral-Small-2506-4bit-DWQ)
🌟 Advertise your project 🚀

Magistral Small 2506 4bit DWQ Parameters and Internals

LLM NameMagistral Small 2506 4bit DWQ
Repository 🤗https://huggingface.co/mlx-community/Magistral-Small-2506-4bit-DWQ 
Base Model(s)  Magistral Small 2506 Bf16   mlx-community/Magistral-Small-2506-bf16
Model Size23.6b
Required VRAM13.3 GB
Updated2026-05-23
Maintainermlx-community
Model Typemistral
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   2.7 GB: 3-of-3
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 Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.52.4
Tokenizer ClassLlamaTokenizerFast
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Magistral Small 2506 4bit DWQ

Best Alternatives
Context / RAM
Downloads
Likes
Devstral Small 2507 4bit DWQ128K / 13.3 GB18612
Chat KTO128K / 47.3 GB70
Chat KTO128K / 47.3 GB60
Devstral Samll 2507 Bf16128K / 46.9 GB371
Devstral Small 2505 Bf16128K / 46.9 GB221
Magistral Small 250640K / 47.3 GB360
...stral Small 2501 Tensopolis V132K / 47.3 GB60
XortronCriminalComputingConfig32K / 47.3 GB72587
Magistral Small 2506 Bf1632K / 46.9 GB3110
Sandmisthink24BKaalpac32K / 47.3 GB320
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Magistral-Small-2506-4bit-DWQ.

Rank the Magistral Small 2506 4bit DWQ 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? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer