LLM Name | Granite 3.3 8B Instruct Fp16 |
Repository ๐ค | https://huggingface.co/mlx-community/granite-3.3-8b-instruct-fp16 |
Base Model(s) | |
Model Size | 8b |
Required VRAM | 16.4 GB |
Updated | 2025-06-09 |
Maintainer | mlx-community |
Model Type | granite |
Instruction-Based | Yes |
Model Files | |
Quantization Type | fp16 |
Model Architecture | GraniteForCausalLM |
License | apache-2.0 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.49.0 |
Tokenizer Class | GPT2Tokenizer |
Padding Token | <|end_of_text|> |
Vocabulary Size | 49159 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...anite 3.2 8B Instruct Bnb 4bit | 128K / 4.5 GB | 482 | 3 |
Granite 3.1 8B Instruct | 128K / 16.4 GB | 354836 | 158 |
Granite 3.2 8B Instruct | 128K / 16.4 GB | 48000 | 85 |
Granite 3.3 8B Instruct | 128K / 16.4 GB | 61372 | 87 |
Granite 3.3 8B Instruct GGUF | 128K / 1.9 GB | 10772 | 4 |
...ranite 3.2 8B Instruct Preview | 128K / 16.4 GB | 723 | 69 |
Granite 3.2 8B Instruct | 128K / 21.5 GB | 31 | 2 |
Granite 3.1 8B Reasoning | 128K / 16.4 GB | 20 | 1 |
Granite 3.0 8B Instruct | 4K / 16.4 GB | 23426 | 201 |
...te 3.0 8B Lora Intrinsics V0.1 | 4K / 32.8 GB | 19 | 2 |
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