LLM Name | Gemma 2 27B 8bit |
Repository ๐ค | https://huggingface.co/mlx-community/gemma-2-27b-8bit |
Base Model(s) | |
Model Size | 27b |
Required VRAM | 28.8 GB |
Updated | 2024-11-13 |
Maintainer | mlx-community |
Model Type | gemma2 |
Model Files | |
Quantization Type | 8bit |
Model Architecture | Gemma2ForCausalLM |
License | gemma |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.42.0.dev0 |
Tokenizer Class | GemmaTokenizer |
Padding Token | <pad> |
Vocabulary Size | 256000 |
Torch Data Type | float32 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Gemma 2 27B It Bnb 4bit | 8K / 15.8 GB | 5402 | 7 |
Gemma 2 27B Bnb 4bit | 8K / 15.8 GB | 4166 | 12 |
Gemma 2 27B It 4bit | 8K / 15.3 GB | 318 | 7 |
GEMMA2 27B NLI 16bit | 8K / 54.7 GB | 17 | 0 |
Gemma 2 27B It 8bit | 8K / 28.8 GB | 69 | 10 |
Gemma 2 27B It 4bit | 8K / 15.8 GB | 48 | 3 |
Gemma 2 27B 4bit | 8K / 15.3 GB | 31 | 0 |
Gemma 2 27B It | 8K / 54.7 GB | 245666 | 439 |
Magnum V4 27B | 8K / 54.7 GB | 533 | 8 |
Gemma 2 27B | 8K / 108.3 GB | 19598 | 177 |
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