What are the hardware requirements for CodeQwen1.5 7B Chat AWQ?

CodeQwen1.5 7B Chat AWQ requires approximately 5.3 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CodeQwen1.5 7B Chat AWQ and how large is it?

CodeQwen1.5 7B Chat AWQ is developed by Qwen, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CodeQwen1.5 7B Chat AWQ perform on standard benchmarks?

CodeQwen1.5 7B Chat AWQ has the following published scores: MMLU 39.37, HumanEval (Python) 87.2. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeQwen1.5 7B Chat AWQ by Qwen — VRAM 5.3GB, 64K context

Name: CodeQwen1.5 7B Chat AWQ
Author: Qwen

CodeQwen1.5 7B Chat AWQ is an open-source language model by Qwen. Features: 7b LLM, VRAM: 5.3GB, Context: 64K, License: other, Quantized, LLM Explorer Score: 0.15, Arc: 35.5, HellaSwag: 54, MMLU: 39.4, GSM8K: 27.9, HumanEval: 87.2.

Arxiv:2309.16609 4-bit Awq Chat Conversational En Endpoints compatible Quantized Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat-AWQ

CodeQwen1.5 7B Chat AWQ Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Applications:

text-to-SQL, bug fix

Primary Use Cases:

long context understanding and generation

Additional Notes

Supports 92 coding languages.

Supported Languages

en (advanced proficiency)

Training Details

Data Sources:

3 trillion tokens of data of codes

Data Volume:

3 trillion tokens

Methodology:

group query attention (GQA) for efficient inference

Context Length:

64000

Model Architecture:

transformer-based decoder-only language model

Input Output

Input Format:

messages with role and content for chat interactions

Accepted Modalities:

text

Output Format:

textual response

Performance Tips:

Use provided hyper-parameters in 'generation_config.json' for best results

LLM Name	CodeQwen1.5 7B Chat AWQ
Repository 🤗	https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat-AWQ
Base Model(s)	Qwen/CodeQwen1.5-7B-Chat Qwen/CodeQwen1.5-7B-Chat
Model Size	7b
Required VRAM	5.3 GB
Updated	2026-07-08
Maintainer	Qwen
Model Type	qwen2
Model Files	4.0 GB: 1-of-2 1.3 GB: 2-of-2
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	65536
Model Max Length	65536
Transformers Version	4.39.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<fim_pad>
Vocabulary Size	92416
Torch Data Type	float16

Rank the CodeQwen1.5 7B Chat 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 CodeQwen1.5 7B Chat AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Arcee Maestro 7B Preview AWQ	128K / 5.6 GB	12	1
Samantha Qwen2 7B AWQ	128K / 5.6 GB	10	0
Dolphin 2.9.2 Qwen2 7B AWQ	128K / 5.6 GB	31	0
CodeQwen1.5 7B AWQ	64K / 5.3 GB	65	2
...nt4 Asym Bf16 Onnx Ryzen Strix	32K / GB	9	1
Qwen2.5 7B Instruct AWQ	32K / 5.6 GB	4511676	48
Qwen2.5 Coder 7B Instruct AWQ	32K / 5.7 GB	563249	1
Qwen2.5 Coder 7B Instruct AWQ	32K / 5.6 GB	316581	24
Qwen2 7B Instruct AWQ	32K / 5.6 GB	20200	23
Qwen1.5 7B Chat AWQ	32K / 5.9 GB	260	13

Note: green Score (e.g. "73.2") means that the model is better than Qwen/CodeQwen1.5-7B-Chat-AWQ.