LLM Name | Granite 3.2 8B Instruct Preview |
Repository ๐ค | https://huggingface.co/ibm-granite/granite-3.2-8b-instruct-preview |
Base Model(s) | |
Model Size | 8b |
Required VRAM | 16.4 GB |
Updated | 2025-03-27 |
Maintainer | ibm-granite |
Model Type | granite |
Instruction-Based | Yes |
Model Files | |
Model Architecture | GraniteForCausalLM |
License | apache-2.0 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.48.2 |
Tokenizer Class | GPT2Tokenizer |
Padding Token | <|end_of_text|> |
Vocabulary Size | 49155 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Granite 3.1 8B Instruct | 128K / 16.4 GB | 90445 | 154 |
Granite 3.2 8B Instruct | 128K / 16.4 GB | 33246 | 64 |
Granite 3.2 8B Instruct | 128K / 21.5 GB | 515 | 2 |
Granite 3.1 8B Reasoning | 128K / 16.4 GB | 37 | 1 |
Granite 3.0 8B Instruct | 4K / 16.4 GB | 26906 | 199 |
...te 3.0 8B Lora Intrinsics V0.1 | 4K / 32.8 GB | 35 | 2 |
...te 3.0 8B Instruct Abliterated | 4K / GB | 2 | 2 |
...anite 3.2 8B Instruct Bnb 4bit | 128K / 4.5 GB | 542 | 3 |
...te 3.2 8B Instruct Abliterated | 128K / 16.4 GB | 270 | 4 |
...te 3.1 8B Instruct Abliterated | 128K / 16.4 GB | 22 | 4 |
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