Granite 4.0 H Tiny 5bit MLX is an open-source language model by mlx-community. Features: LLM, VRAM: 4.8GB, Context: 128K, License: apache-2.0, Quantized.
5-bit 5bit Apple-silicon Base model:ibm-granite/granite... Base model:quantized:ibm-grani... Conversational En Granite Granitemoehybrid Hybrid Ibm Instruct Long-context Mamba2 Mlx Moe Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/granite-4.0-h-tiny-5bit-MLX
Granite 4.0 H Tiny 5bit MLX Parameters and Internals
| LLM Name | Granite 4.0 H Tiny 5bit MLX |
| Repository 🤗 | https://huggingface.co/mlx-community/granite-4.0-h-tiny-5bit-MLX |
| Base Model(s) | |
| Required VRAM | 4.8 GB |
| Updated | 2026-03-28 |
| Maintainer | mlx-community |
| Model Type | granitemoehybrid |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 5bit |
| 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 |
Best Alternatives to Granite 4.0 H Tiny 5bit MLX
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Granite 4.0 Tiny Preview | 128K / 13.3 GB | 26003 | 182 |
| Granite 4.0 H Small | 128K / 64.4 GB | 85918 | 304 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/granite-4.0-h-tiny-5bit-MLX .
Rank the Granite 4.0 H Tiny 5bit MLX Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 52052 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a