Granite 4.1 8B 8bit is an open-source language model by mlx-community. Features: 8b LLM, VRAM: 9.4GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.41, ELO: 1307.
| LLM Name | Granite 4.1 8B 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/granite-4.1-8b-8bit |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 9.4 GB |
| Updated | 2026-06-21 |
| Maintainer | mlx-community |
| Model Type | granite |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | GraniteForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.53.3 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...anite 3.2 8B Instruct Bnb 4bit | 128K / 4.5 GB | 553 | 3 |
| Granite 3.3 8B Instruct Fp16 | 128K / 16.4 GB | 47 | 3 |
| Granite 3.3 8B Instruct 8bit | 128K / 8.6 GB | 36 | 2 |
| Granite 4.1 8B | 128K / 17.6 GB | 21803 | 161 |
| Granite 3.1 8B Instruct | 128K / 16.4 GB | 73170 | 168 |
| Granite 4.1 8B Base | 128K / 16.8 GB | 18630 | 25 |
| Granite Guardian 4.1 8B | 128K / 16.8 GB | 10001 | 28 |
| Granite 4.1 8B Fp8 | 128K / 9.7 GB | 11768 | 12 |
| Granite 3.1 8B Reasoning | 128K / 16.4 GB | 4 | 1 |
| Granite 3.1 8B Instruct | 128K / 16.4 GB | 124 | 1 |
🆘 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! 🌟