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

Codestral 22B V0.1 EXL2 5.0bpw by bullerwins

 »  All LLMs  »  bullerwins  »  Codestral 22B V0.1 EXL2 5.0bpw   URL Share it on

  16   
  5-bit   Autotrain compatible   Code   Exl2   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bullerwins/Codestral-22B-v0.1-exl2_5.0bpw 

Codestral 22B V0.1 EXL2 5.0bpw Benchmarks

LLME Score: 0.17208
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Codestral 22B V0.1 EXL2 5.0bpw Parameters and Internals

Model Type 
code generation, text completion
Use Cases 
Areas:
research, software development
Primary Use Cases:
code generation, code explanation, software development add-ons
Limitations:
Does not have any moderation mechanisms
Additional Notes 
Codestral-22B-v0.1 is recommended to be used with mistral_inference for optimal performance.
Training Details 
Methodology:
exllamav2 0.1.1
LLM NameCodestral 22B V0.1 EXL2 5.0bpw
Repository 🤗https://huggingface.co/bullerwins/Codestral-22B-v0.1-exl2_5.0bpw 
Model Size22b
Required VRAM14.2 GB
Updated2025-06-09
Maintainerbullerwins
Model Typemistral
Model Files  8.6 GB: 1-of-2   5.6 GB: 2-of-2
Supported Languagescode
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
LicenseMNPL-0.1
Context Length32768
Model Max Length32768
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32768
Torch Data Typebfloat16
Codestral 22B V0.1 EXL2 5.0bpw (bullerwins/Codestral-22B-v0.1-exl2_5.0bpw)

Best Alternatives to Codestral 22B V0.1 EXL2 5.0bpw

Best Alternatives
Context / RAM
Downloads
Likes
MwM 22B Instruct128K / 44.7 GB60
... Instruct 0.2 Chkpt 200 16 Bit128K / 44.7 GB411
...l 22B V0.1 Hf FIM Fix Bnb 4bit32K / 13.1 GB81
Text2cypher Codestral 16bit32K / 44.7 GB123
Codestral 22B V0.1 EXL2 8.0bpw32K / 20.9 GB503
... Abliterated V3.8.0bpw H8 EXL232K / 21.2 GB141
...estral 22B V0.1 Hf 2 2bpw EXL232K / 6.6 GB151
Codestral 22B V0.1 EXL2 6.0bpw32K / 16.9 GB111
MS Schisandra 22B V0.2128K / 44.7 GB119
...ntheon RP Pure 1.6.2 22B Small128K / 44.7 GB1231
Note: green Score (e.g. "73.2") means that the model is better than bullerwins/Codestral-22B-v0.1-exl2_5.0bpw.

Rank the Codestral 22B V0.1 EXL2 5.0bpw 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? 48046 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.
Release v20241124
  Support LLM Explorer