CodeQwen1.5 7B Chat AWQ is an open-source language model by Qwen. Features: 7b LLM, VRAM: 5.3GB, Context: 64K, License: other, Quantized, HF Score: 43.3, LLM Explorer Score: 0.17, Arc: 35.5, HellaSwag: 54, MMLU: 39.4, TruthfulQA: 44.8, WinoGrande: 58, 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 Benchmarks
ARC: 35.49 vs 96.7 (so35)-63.3%
HellaSwag: 54.03 vs 95.3 (gpt4)-43.3%
MMLU: 39.37 vs 88.3 (so35)-55.4%
TruthfulQA: 44.75 vs 59 (gpt4)-24.2%
WinoGrande: 58.01 vs 87.5 (gpt4)-33.7%
GSM8K: 27.9 vs 96.4 (so35)-71.1%
HumanEvalA: 54.95
Python Eva: 87.2 vs 92 (so35)-5.2%
Java Eval: 61.04
Javascript: 70.31
CPP Eval: 67.85
PHP Eval: 69.22
Julia Eval: 51.89
D Eval: 22.71
Lua Eval: 32.89
R Eval: 39.86
Racket Eva: 29.38
Rust Eval: 67.49
Swift Eval: 59.59
LLME Score: 0.16769
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
CodeQwen1.5 7B Chat AWQ Parameters and Internals
| Model Type |
| |||||||||||||||
| Use Cases |
| |||||||||||||||
| Additional Notes |
| |||||||||||||||
| Supported Languages |
| |||||||||||||||
| Training Details |
| |||||||||||||||
| Input Output |
|
| LLM Name | CodeQwen1.5 7B Chat AWQ |
| Repository 🤗 | https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat-AWQ |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 5.3 GB |
| Updated | 2026-03-31 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Model Files | |
| 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 |
Best Alternatives to CodeQwen1.5 7B Chat AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Samantha Qwen2 7B AWQ | 128K / 5.6 GB | 6 | 0 |
| Dolphin 2.9.2 Qwen2 7B AWQ | 128K / 5.6 GB | 14 | 0 |
| CodeQwen1.5 7B AWQ | 64K / 5.3 GB | 110 | 2 |
| Qwen2.5 7B Instruct AWQ | 32K / 5.6 GB | 708715 | 40 |
| Qwen2.5 Coder 7B Instruct AWQ | 32K / 5.6 GB | 256217 | 21 |
| Qwen2 7B Instruct AWQ | 32K / 5.6 GB | 22897 | 22 |
| Qwen1.5 7B Chat AWQ | 32K / 5.9 GB | 327 | 13 |
| Qwen1.5 7B AWQ W4 G128 | 32K / 5.9 GB | 6 | 0 |
| Qwen2.5 7B Instruct 1M 4bit | 986K / 4.3 GB | 422 | 10 |
| ...B Instruct 1M Unsloth Bnb 4bit | 986K / 7.5 GB | 77 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/CodeQwen1.5-7B-Chat-AWQ .
Rank the CodeQwen1.5 7B Chat 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! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a