Codestral 22B V0.1 by mistralai

 »  All LLMs  »  mistralai  »  Codestral 22B V0.1   URL Share it on

Codestral 22B V0.1 is an open-source language model by mistralai. Features: 22b LLM, VRAM: 44.7GB, License: MNPL-0.1, LLM Explorer Score: 0.28.

  Code   Mistral   Mistral-common   Region:us   Safetensors   Sharded   Tensorflow   Vllm

Codestral 22B V0.1 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Codestral 22B V0.1 Parameters and Internals

Model Type 
code generation
Use Cases 
Areas:
software development, question answering about code
Primary Use Cases:
generate code, write documentation, explain code, factorize code, predict middle tokens in code
Limitations:
no moderation mechanisms
Additional Notes 
Codestral-22B-v0.1 does not have any moderation mechanisms and is trained on a diverse dataset of 80+ programming languages.
Supported Languages 
Python (high), Java (high), C (high), C++ (high), JavaScript (high), Bash (high)
LLM NameCodestral 22B V0.1
Repository 🤗https://huggingface.co/mistralai/Codestral-22B-v0.1 
Model Size22b
Required VRAM44.7 GB
Updated2026-07-16
Maintainermistralai
Model Files  44.5 GB   4.9 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   4.9 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   4.9 GB: 7-of-9   5.0 GB: 8-of-9   5.0 GB: 9-of-9
Supported Languagescode
Model ArchitectureMambaSSM
LicenseMNPL-0.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32768

Quantized Models of the Codestral 22B V0.1

Model
Likes
Downloads
VRAM
...t2cypher Codestral Q4 K M Gguf523213 GB
Codestral 22B V0.1 GGUF13618 GB
Codestral 22B V0.1 GGUF01838 GB
...xt2cypher Codestral 16bit Gguf04744 GB
Text2cypher Codestral 16bit3744 GB

Rank the Codestral 22B V0.1 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? 55138 in total.

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