What are the hardware requirements for CodeLlama 7B Instruct AWQ?

CodeLlama 7B Instruct AWQ requires approximately 3.9 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CodeLlama 7B Instruct AWQ and how large is it?

CodeLlama 7B Instruct AWQ is developed by TheBloke, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate CodeLlama 7B Instruct AWQ?

CodeLlama 7B Instruct AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

CodeLlama 7B Instruct AWQ by TheBloke — VRAM 3.9GB, 16K context

Name: CodeLlama 7B Instruct AWQ
Author: TheBloke

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

Arxiv:2308.12950 4-bit Awq Code Codegen Instruct Llama Llama2 Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-AWQ

CodeLlama 7B Instruct AWQ Parameters and Internals

Model Type

llama

Use Cases

Primary Use Cases:

Code completion, Infilling, Instructions/chat

Limitations:

Use in languages other than English is out of scope

Considerations:

Code Llama’s potential outputs cannot be predicted in advance, and the model may produce inaccurate or objectionable responses.

Additional Notes

Supports AWQ and GPTQ quantization methods for reduced computational footprint.

Training Details

Data Sources:

Evol Instruct Code

Data Volume:

Code Llama and its variants have been trained between January 2023 and July 2023.

Methodology:

Optimized transformer architecture

Context Length:

4096

Training Time:

400K GPU hours

Hardware Used:

A100-80GB GPUs

Model Architecture:

Auto-regressive language model

Responsible Ai Considerations

Mitigation Strategies:

Developers should perform safety testing and tuning tailored to their specific applications of the model.

Input Output

Input Format:

Models input text only

Accepted Modalities:

text

Output Format:

Models generate text only

LLM Name	CodeLlama 7B Instruct AWQ
Repository 🤗	https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-AWQ
Model Name	CodeLlama 7B Instruct
Model Creator	Meta
Base Model(s)	codellama/CodeLlama-7b-instruct-hf codellama/CodeLlama-7b-instruct-hf
Model Size	7b
Required VRAM	3.9 GB
Updated	2026-07-21
Maintainer	TheBloke
Model Type	llama
Instruction-Based	Yes
Model Files	3.9 GB
Supported Languages	code
AWQ Quantization	Yes
Quantization Type	awq
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.33.0.dev0
Tokenizer Class	CodeLlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32016
Torch Data Type	bfloat16

Rank the CodeLlama 7B Instruct AWQ capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to CodeLlama 7B Instruct AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...ama 7B Instruct Hf W4 G128 AWQ	16K / 3.9 GB	6	0
...ruct Solidity Bnb 4bit Smashed	16K / 4.2 GB	6	0
...B Instruct Hf Bnb 4bit Smashed	16K / 4.2 GB	6	0
CodelLama7B Inst DPO 7K Mlx	16K / 4.2 GB	49	4
...eLlama 7B Instruct Hf 4bit MLX	16K / 4.2 GB	84	3
...6.7B Instruct 8.0bpw H8 EXL2 2	16K / 6.8 GB	7	2
...6.7B Instruct 3.0bpw H6 EXL2 2	16K / 2.8 GB	8	1
... 7B Instruct Nf4 Fp16 Upscaled	16K / 13.5 GB	9	0
CodeLlama 7B Instruct Fp16	16K / 13.5 GB	24	7
...Llama 7B Instruct Bf16 Sharded	16K / 13.5 GB	29	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-7B-Instruct-AWQ.