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

Devstral Small 2505 Unsloth Bnb 4bit by unsloth

 »  All LLMs  »  unsloth  »  Devstral Small 2505 Unsloth Bnb 4bit   URL Share it on

  121   

Devstral Small 2505 Unsloth Bnb 4bit is an open-source language model by unsloth. Features: 13.1b LLM, VRAM: 15GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.2.

  4-bit   4bit   Ar Base model:mistralai/devstral-... Base model:quantized:mistralai...   Bitsandbytes   Bn   Conversational   De   En   Es   Fa   Fr   Hi   Id   It   Ja   Ko   Mistral   Ms   Ne   Pl   Pt   Quantized   Region:us   Ro   Ru   Safetensors   Sharded   Sr   Sv   Tensorflow   Tr   Uk   Unsloth   Vi   Vllm   Zh
Model Card on HF 🤗: https://huggingface.co/unsloth/Devstral-Small-2505-unsloth-bnb-4bit 

Devstral Small 2505 Unsloth Bnb 4bit Benchmarks

LLME Score: 0.19757
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Devstral Small 2505 Unsloth Bnb 4bit (unsloth/Devstral-Small-2505-unsloth-bnb-4bit)
🌟 Advertise your project 🚀

Devstral Small 2505 Unsloth Bnb 4bit Parameters and Internals

LLM NameDevstral Small 2505 Unsloth Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Devstral-Small-2505-unsloth-bnb-4bit 
Base Model(s)  Devstral Small 2505   mistralai/Devstral-Small-2505
Model Size13.1b
Required VRAM15 GB
Updated2026-05-06
Maintainerunsloth
Model Typemistral
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   5.0 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 Length131072
Model Max Length131072
Transformers Version4.52.1
Tokenizer ClassLlamaTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Devstral Small 2505 Unsloth Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
NemoMix Unleashed EXL2 4bpw1000K / 7.3 GB189
...iminalComputingConfig Mlx 8Bit32K / 25 GB953
...0.88 07.02 RP DPO Merged 16bit32K / 14.4 GB60
...eZephir Sft Instruct Ead 16bit32K / 14.4 GB560
...cr To Json V1 HQQ 1bit Smashed32K / 1.6 GB50
...cr To Json V1 HQQ 4bit Smashed32K / 4.2 GB50
ScikitLLM Model EXL232K / 3 GB91
Chargen V2 8bpw EXL232K / 7.4 GB21
...tral PairRM DPO 8.0bpw H8 EXL232K / 7.4 GB52
HamSter 0.2 8.0bpw H8 EXL232K / 7.4 GB11
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Devstral-Small-2505-unsloth-bnb-4bit.

Rank the Devstral Small 2505 Unsloth Bnb 4bit 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? 53518 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