Arxiv:1910.09700 4-bit Autotrain compatible Conversational Endpoints compatible Gptq Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Rank the Qwen Qwen1.5 32B 4 Bit Gptq 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! 🌟
Best Alternatives to Qwen Qwen1.5 32B 4 Bit Gptq
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Qwen1.5 32B Chat GPTQ Int4 | — | 32K / 19.5 GB | 3192 | 26 |
| Qwen1.5 32B Chat GPTQ Int8 | — | 32K / 34.9 GB | 13 | 0 |
| ...wen1.5 32B Chat 3.0bpw H6 EXL2 | — | 32K / 13.7 GB | 1 | 1 |
| Qwen1.5 32B Chat Quip 3bit | — | 32K / 14.8 GB | 2 | 1 |
| ...wen1.5 32B Chat 4.0bpw H6 EXL2 | — | 32K / 17.7 GB | 1 | 1 |
| Qwen1.5 32B 4bit | — | 32K / 19.5 GB | 1 | 1 |
| Deita 32B EXL2 8.0bpw | — | 32K / 33.2 GB | 2 | 1 |
| Qwen1.5 32B Chat 4bit | — | 32K / 54.9 GB | 2 | 3 |
| Qwen1.5 32B Chat 8bit | — | 32K / 54.9 GB | 2 | 1 |
| Qwen1.5 32B Chat AWQ | — | 32K / 21.2 GB | 1049 | 14 |
Qwen Qwen1.5 32B 4 Bit Gptq Parameters and Internals
| LLM Name | Qwen Qwen1.5 32B 4 Bit Gptq |
| Repository | Open on 🤗 |
| Model Size | 32b |
| Required VRAM | 19.2 GB |
| Updated | 2024-07-01 |
| Maintainer | SotiriosKastanas |
| Model Type | qwen2 |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Initializer Range | 0.02 |
| Torch Data Type | float16 |
| Errors | replace |
What open-source LLMs or SLMs are you in search of? 34238 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801