Model Type |
| ||||||
Additional Notes |
| ||||||
Supported Languages |
| ||||||
Training Details |
| ||||||
Input Output |
|
LLM Name | Qwen1.5 110B Chat GPTQ Int4 |
Repository ๐ค | https://huggingface.co/study-hjt/Qwen1.5-110B-Chat-GPTQ-Int4 |
Base Model(s) | |
Model Size | 110b |
Required VRAM | 61.5 GB |
Updated | 2025-03-23 |
Maintainer | study-hjt |
Model Type | qwen2 |
Model Files | |
Supported Languages | en |
GPTQ Quantization | Yes |
Quantization Type | gptq |
Model Architecture | Qwen2ForCausalLM |
License | other |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.39.3 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 152064 |
Torch Data Type | float16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen1.5 110B Chat GPTQ Int4 | 32K / 61.7 GB | 37 | 17 |
Qwen1.5 110B Chat 4bit | 32K / 62.2 GB | 7 | 5 |
Qwen1.5 110B Chat 8bit | 32K / 179.8 GB | 5 | 1 |
...n1.5 110B Chat 3.35bpw H6 EXL2 | 32K / 49 GB | 8 | 1 |
...n1.5 110B Chat 3.25bpw H6 EXL2 | 32K / 47.7 GB | 9 | 1 |
Qwen1.5 110B 4bit | 8K / 62.2 GB | 4 | 1 |
Qwen1.5 110B Chat | 32K / 158.3 GB | 4755 | 125 |
Qwen1.5 110B | 32K / 221.7 GB | 592 | 97 |
Qwen1.5 110B Chat AWQ | 32K / 61.7 GB | 15 | 9 |
Qwen1.5 110B Chat AWQ | 32K / 61.1 GB | 8 | 0 |
๐ 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! ๐