Granite 4.0 H Micro 8bit is an open-source language model by mlx-community. Features: 898.4m LLM, VRAM: 3.4GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.21.
| LLM Name | Granite 4.0 H Micro 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/granite-4.0-h-micro-8bit |
| Base Model(s) | |
| Model Size | 898.4m |
| Required VRAM | 3.4 GB |
| Updated | 2026-08-02 |
| Maintainer | mlx-community |
| Model Type | granitemoehybrid |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | GraniteMoeHybridForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.56.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |