LLM EXPLORER 59,420 MODELS INDEXED

CodeLlama 70B Python Hf 2.65bpw H6 EXL2 by LoneStriker

By LoneStriker · 5 downloads
HF Repo ↗ Copy URL

CodeLlama 70B Python Hf 2.65bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 70b LLM, VRAM: 23.5GB, Context: 2K, License: llama2, Quantized, Code Generating, LLM Explorer Score: 0.11.

  Arxiv:2308.12950   Code   Codegen   Endpoints compatible   Exl2   Llama   Llama2   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/CodeLlama-70b-Python-hf-2.65bpw-h6-exl2 

CodeLlama 70B Python Hf 2.65bpw H6 EXL2 Parameters and Internals

Model Type 
text generation, code synthesis
Use Cases 
Areas:
commercial, research
Applications:
code synthesis, code understanding tasks, code assistant and generation
Primary Use Cases:
Python programming language
Limitations:
Use in languages other than English.
Considerations:
Developers should perform safety testing tailored to their specific applications.
Additional Notes 
This is a static model trained on an offline dataset.
Supported Languages 
programming_languages (Python), proficiency_level (specialist)
Training Details 
Data Sources:
offline dataset
Methodology:
fine-tuned with up to 16k tokens
Hardware Used:
A100-80GB GPUs
Model Architecture:
auto-regressive language model that uses an optimized transformer architecture
Safety Evaluation 
Ethical Considerations:
Testing conducted to date has been in English, and has not covered all scenarios. The model may produce inaccurate or objectionable responses.
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
LLM NameCodeLlama 70B Python Hf 2.65bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/CodeLlama-70b-Python-hf-2.65bpw-h6-exl2 
Model Size70b
Required VRAM23.5 GB
Updated2026-06-25
MaintainerLoneStriker
Model Typellama
Model Files  8.5 GB: 1-of-3   8.6 GB: 2-of-3   6.4 GB: 3-of-3
Supported Languagescode
Quantization Typeexl2
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length2048
Model Max Length2048
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32016
Torch Data Typebfloat16

Best Alternatives to CodeLlama 70B Python Hf 2.65bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...rpreter CL 70B 4.65bpw H6 EXL216K / 40.6 GB50
CodeLlama 70B Hf 4bit MLX16K / 39.1 GB11212
...odeLlama 70B Hf 4.0bpw H6 EXL216K / 35 GB41
...odeLlama 70B Hf 2.4bpw H6 EXL216K / 21.3 GB31
CodeLLaMA 70B Hf Fp1616K / 138.7 GB82
...Llama 70B Instruct Hf 4bit MLX4K / 39.1 GB41725
...deLlama 70B Python Hf 4bit MLX4K / 39.1 GB10811
...70B Instruct Nf4 Fp16 Upscaled4K / 138.7 GB101
...70B Instruct Hf 5.0bpw H6 EXL22K / 43.6 GB56
...70B Instruct Hf 2.4bpw H6 EXL22K / 21.3 GB61
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/CodeLlama-70b-Python-hf-2.65bpw-h6-exl2.