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

Mistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4 by mlx-community

 »  All LLMs  »  mlx-community  »  Mistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4   URL Share it on

  277   

Mistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4 is an open-source language model by mlx-community. Features: 24b LLM, VRAM: 12.5GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.24.

  4-bit Base model:mistralai/devstral-... Base model:quantized:mistralai...   Conversational   Instruct   Mistral-common   Mistral3   Mlx   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-MXFP4 

Mistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4 Benchmarks

LLME Score: 0.23894
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4 (mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-MXFP4)
🌟 Advertise your project 🚀

Mistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4 Parameters and Internals

LLM NameMistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4
Repository 🤗https://huggingface.co/mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-MXFP4 
Base Model(s)  ...tral Small 2 24B Instruct 2512   mistralai/Devstral-Small-2-24B-Instruct-2512
Model Size24b
Required VRAM12.5 GB
Updated2026-05-23
Maintainermlx-community
Model Typemistral3
Instruction-BasedYes
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   1.9 GB: 3-of-3
Model ArchitectureMistral3ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.0.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<pad>

Best Alternatives to Mistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4

Best Alternatives
Context / RAM
Downloads
Likes
...all 3.2 24B Instruct 2506 Bf160K / 46.9 GB681
...all 3.2 24B Instruct 2506 8bit0K / 25 GB2394
...l 2 24B Instruct 2512 MLX 8Bit0K / 25 GB10886
...all 3.2 24B Instruct 2506 4bit0K / 13.3 GB3452
Devstral Small 2507 GGUF0K / 0.9 GB343577
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-MXFP4.

Rank the Mistralai Devstral Small 2 24B Instruct 2512 MLX MXFP4 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? 53972 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