Arxiv:1910.09700 4-bit Autotrain compatible Conversational Endpoints compatible Gptq Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Xu-Ouyang/Qwen2-7B-int4-GPTQ-wikitext2
Qwen2 7B Int4 GPTQ Wikitext2 Benchmarks
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)
Qwen2 7B Int4 GPTQ Wikitext2 Parameters and Internals
| LLM Name | Qwen2 7B Int4 GPTQ Wikitext2 |
| Repository 🤗 | https://huggingface.co/Xu-Ouyang/Qwen2-7B-int4-GPTQ-wikitext2 |
| Model Size | 7b |
| Required VRAM | 5.6 GB |
| Updated | 2025-09-23 |
| Maintainer | Xu-Ouyang |
| Model Type | qwen2 |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen2 7B Int4 GPTQ Wikitext2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CodeQwen1.5 7B Chat GPTQ Int4 | 64K / 4.9 GB | 6 | 0 |
| Qwen2.5 7B Instruct GPTQ Int4 | 32K / 5.6 GB | 254621 | 28 |
| Qwen2.5 7B Instruct GPTQ Int8 | 32K / 8.9 GB | 15817 | 15 |
| Qwen2 7B Instruct GPTQ Int8 | 32K / 8.9 GB | 21582 | 17 |
| ....5 Coder 7B Instruct GPTQ Int4 | 32K / 5.6 GB | 2393 | 8 |
| ....5 Coder 7B Instruct GPTQ Int8 | 32K / 8.9 GB | 1534 | 4 |
| Qwen2 7B Instruct GPTQ Int4 | 32K / 5.6 GB | 2131 | 29 |
| Qwen1.5 7B Int3 GPTQ Wikitext2 | 32K / 5 GB | 5 | 0 |
| Qwen1.5 7B Int4 GPTQ Wikitext2 | 32K / 5.8 GB | 16 | 0 |
| AVA Qwen1.5 7B Chat Gptq 4bit | 32K / 5.8 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Xu-Ouyang/Qwen2-7B-int4-GPTQ-wikitext2 .
Rank the Qwen2 7B Int4 GPTQ Wikitext2 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124