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

Devstral Small 2 24B Instruct 2512 Bf16 by mlx-community

 »  All LLMs  »  mlx-community  »  Devstral Small 2 24B Instruct 2512 Bf16   URL Share it on

  367   

Devstral Small 2 24B Instruct 2512 Bf16 is an open-source language model by mlx-community. Features: 24b LLM, VRAM: 47.8GB, Context: 384K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.23.

Base model:mistralai/devstral-... Base model:quantized:mistralai...   Bf16   Conversational   Fp8   Image-text-to-text   Instruct   Mistral-common   Mistral3   Mlx   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Devstral-Small-2-24B-Instruct-2512-bf16 

Devstral Small 2 24B Instruct 2512 Bf16 Benchmarks

LLME Score: 0.22855
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Devstral Small 2 24B Instruct 2512 Bf16 (mlx-community/Devstral-Small-2-24B-Instruct-2512-bf16)

Devstral Small 2 24B Instruct 2512 Bf16 Parameters and Internals

LLM NameDevstral Small 2 24B Instruct 2512 Bf16
Repository 🤗https://huggingface.co/mlx-community/Devstral-Small-2-24B-Instruct-2512-bf16 
Base Model(s)  ...tral Small 2 24B Instruct 2512   mistralai/Devstral-Small-2-24B-Instruct-2512
Model Size24b
Required VRAM47.8 GB
Updated2026-07-23
Maintainermlx-community
Instruction-BasedYes
Model Files  5.2 GB: 1-of-10   5.2 GB: 2-of-10   5.2 GB: 3-of-10   5.1 GB: 4-of-10   5.2 GB: 5-of-10   5.2 GB: 6-of-10   5.1 GB: 7-of-10   5.2 GB: 8-of-10   5.1 GB: 9-of-10   1.3 GB: 10-of-10
Model ArchitectureMambaSSM
Licenseapache-2.0
Context Length393216
Model Max Length393216
Tokenizer ClassTokenizersBackend
Padding Token<pad>
Vocabulary Size131072

Best Alternatives to Devstral Small 2 24B Instruct 2512 Bf16

Best Alternatives
Context / RAM
Downloads
Likes
...tral Small 2 24B Instruct 2512384K / 51.6 GB240440618
...al Small 3.2 24B Instruct 2506128K / 48.2 GB633788597
Magistral Small 2509128K / 48.2 GB19439302
Devstral Small 2507128K / 47.3 GB42080368
Devstral Small 2505128K / 47.3 GB5094867
Magistral Small 250640K / 47.3 GB18796609
Magistral Small 250740K / 47.3 GB403104
...al Small 3.1 24B Instruct 25030K / 48.2 GB1586911369
...istral Small 24B Instruct 25010K / 47.3 GB74648960
...al Small 3.2 24B Instruct 25060K / 48.2 GB525616
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Devstral-Small-2-24B-Instruct-2512-bf16.

Rank the Devstral Small 2 24B Instruct 2512 Bf16 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? 55346 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
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
  Support LLM Explorer