LLM EXPLORER 59,420 MODELS INDEXED

CodeLlama 70B Hf AWQ by TheBloke

By TheBloke · 13 downloads
HF Repo ↗ Copy URL

CodeLlama 70B Hf AWQ is an open-source language model by TheBloke. Features: 70b LLM, VRAM: 36.6GB, Context: 16K, License: llama2, Quantized, Code Generating, LLM Explorer Score: 0.11.

  Arxiv:2308.12950   4-bit   Awq Base model:codellama/codellama... Base model:quantized:codellama...   Code   Codegen   Llama   Llama2   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-70B-hf-AWQ 

CodeLlama 70B Hf AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
commercial, research
Applications:
code synthesis, understanding tasks
Primary Use Cases:
code assistant and generation applications
Limitations:
English only, not for use in prohibited manners
Additional Notes 
Model trained between January 2023 and January 2024. Supported by NVidia GPUs only for AWQ models.
Supported Languages 
English (commercial and research use), Other programming languages (commercial and research use)
Training Details 
Methodology:
optimized transformer architecture
Context Length:
16000
Hardware Used:
A100-80GB GPUs
Model Architecture:
auto-regressive language model
Responsible Ai Considerations 
Transparency:
Outputs cannot be predicted in advance; may produce inaccurate or objectionable responses.
Mitigation Strategies:
Perform safety testing and tuning tailored to specific applications.
Input Output 
Input Format:
text only
Accepted Modalities:
text
Output Format:
text generation
LLM NameCodeLlama 70B Hf AWQ
Repository 🤗https://huggingface.co/TheBloke/CodeLlama-70B-hf-AWQ 
Model NameCodeLlama 70B
Model CreatorCode Llama
Base Model(s)  CodeLlama 70B Hf   codellama/CodeLlama-70b-hf
Model Size70b
Required VRAM36.6 GB
Updated2026-05-21
MaintainerTheBloke
Model Typellama
Model Files  9.9 GB: 1-of-4   9.9 GB: 2-of-4   9.9 GB: 3-of-4   6.9 GB: 4-of-4
Supported Languagescode
AWQ QuantizationYes
Quantization Typeawq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32016
Torch Data Typefloat16

Best Alternatives to CodeLlama 70B Hf AWQ

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 70B Instruct AWQ4K / 36.6 GB29713
CodeLlama 70B Python AWQ4K / 36.6 GB286
...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
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-70B-hf-AWQ.