LLM Name | Gemma 3 270M It 8bit |
Repository ๐ค | https://huggingface.co/mlx-community/gemma-3-270m-it-8bit |
Base Model(s) | |
Model Size | 270m |
Required VRAM | 0.5 GB |
Updated | 2025-08-28 |
Maintainer | mlx-community |
Model Type | gemma3_text |
Model Files | |
Quantization Type | 8bit |
Model Architecture | Gemma3ForCausalLM |
License | gemma |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.55.0.dev0 |
Tokenizer Class | GemmaTokenizer |
Padding Token | <pad> |
Vocabulary Size | 262144 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...mma 3 270M It Unsloth Bnb 4bit | 32K / 0.4 GB | 25543 | 2 |
Gemma 3 270M It MLX 8bit | 32K / 0.5 GB | 9869 | 2 |
Gemma 3 270M It Qat MLX 4bit | 32K / 0.2 GB | 3461 | 3 |
Gemma 3 270M It Bnb 4bit | 32K / 0.4 GB | 3089 | 3 |
...3 270M It Qat Q4 0 Unquantized | 32K / 0.5 GB | 558 | 11 |
Gemma 3 270M It 4bit | 32K / 0.2 GB | 943 | 5 |
...ma 3 270M Qat Q4 0 Unquantized | 32K / 0.5 GB | 166 | 8 |
Gemma 3 270M | 32K / 0.5 GB | 82276 | 667 |
Gemma 3 270M It | 32K / 0.5 GB | 110714 | 355 |
Gemma 3 270M It | 32K / 0.5 GB | 63423 | 12 |
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