Model Type |
| ||||||
Additional Notes |
| ||||||
Supported Languages |
| ||||||
Input Output |
|
LLM Name | Qwen2.5 Coder 32B Instruct 3bit |
Repository ๐ค | https://huggingface.co/mlx-community/Qwen2.5-Coder-32B-Instruct-3bit |
Base Model(s) | |
Model Size | 32b |
Required VRAM | 14.3 GB |
Updated | 2024-12-08 |
Maintainer | mlx-community |
Model Type | qwen2 |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
Quantization Type | 3bit |
Generates Code | Yes |
Model Architecture | Qwen2ForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.43.1 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 152064 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...wen2.5 Coder 32B Instruct 4bit | 32K / 18.5 GB | 2488 | 6 |
...truct Gptqmodel 4bit Vortex V1 | 32K / 21.3 GB | 747 | 11 |
...wen2.5 Coder 32B Instruct 8bit | 32K / 34.9 GB | 911 | 7 |
Rombos Coder V2.5 Qwen 32B | 128K / 65.8 GB | 308 | 6 |
Qwen2.5 Coder 32B Instruct | 32K / 65.8 GB | 217679 | 1220 |
Qwen2.5 Coder 32B Instruct AWQ | 32K / 19.4 GB | 17373 | 15 |
...5 Coder 32B Instruct GPTQ Int8 | 32K / 35.1 GB | 10882 | 12 |
...5 Coder 32B Instruct GPTQ Int4 | 32K / 19.5 GB | 10370 | 8 |
...wen2.5 Coder 32B Instruct Bf16 | 32K / 65.9 GB | 654 | 9 |
Qwen2.5 Coder 32B Instruct | 32K / 65.8 GB | 625 | 5 |
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