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

CodeLlama 7B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  CodeLlama 7B AWQ   URL Share it on

  126   

CodeLlama 7B AWQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 3.9GB, Context: 16K, License: llama2, Quantized, Code Generating, LLM Explorer Score: 0.09.

  Arxiv:2308.12950   4-bit   Awq Base model:codellama/codellama... Base model:quantized:codellama...   Code   Codegen   Llama   Llama2   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-7B-AWQ 

CodeLlama 7B AWQ Benchmarks

LLME Score: 0.0949
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeLlama 7B AWQ (TheBloke/CodeLlama-7B-AWQ)
🌟 Advertise your project 🚀

CodeLlama 7B AWQ Parameters and Internals

Model Type 
code synthesis, text generation
Use Cases 
Areas:
commercial, research
Applications:
code assistant, code generation
Primary Use Cases:
code synthesis, understanding tasks
Limitations:
Not tested in languages other than English
Additional Notes 
Trained with Meta's Research Super Cluster, emission offset by Meta’s sustainability program. Compatible with AutoAWQ and vLLM. Not compatible with Huggingface Text Generation Inference (TGI) yet.
Supported Languages 
English (fully supported)
Training Details 
Methodology:
Training libraries and RSC
Hardware Used:
A100-80GB
Model Architecture:
Optimized transformer architecture
Input Output 
Input Format:
text prompts
Accepted Modalities:
text
Output Format:
text
LLM NameCodeLlama 7B AWQ
Repository 🤗https://huggingface.co/TheBloke/CodeLlama-7B-AWQ 
Model NameCodeLlama 7B
Model CreatorMeta
Base Model(s)  CodeLlama 7B Hf   codellama/CodeLlama-7b-hf
Model Size7b
Required VRAM3.9 GB
Updated2026-05-01
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
Supported Languagescode
AWQ QuantizationYes
Quantization Typeawq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.33.0.dev0
Tokenizer ClassCodeLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32016
Torch Data Typebfloat16

Best Alternatives to CodeLlama 7B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...Llama 7B Python Hf W4 G128 AWQ16K / 3.9 GB12320
CodeLlama 7B Python AWQ16K / 3.9 GB1804
CodeLlama 7B Instruct AWQ16K / 3.9 GB904
...ama 7B Instruct Hf W4 G128 AWQ16K / 3.9 GB170
Llama 2 Coder 7B AWQ4K / 3.9 GB793
...eepseek Coder 7B Base V1.5 AWQ4K / 4.8 GB00
CodeLlama 7B Java 16bit16K / 13.5 GB70
Codellama 7B Bnb 4bit16K / 3.9 GB32149
...ruct Solidity Bnb 4bit Smashed16K / 4.2 GB60
...lama 7B Tofuagent Contpretrain16K / 13.5 GB50
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-7B-AWQ.

Rank the CodeLlama 7B AWQ 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? 53472 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