LLM EXPLORER 59,598 MODELS INDEXED

Granite 4.1 30B Mxfp8 by mlx-community

By mlx-community · 328 downloads
HF Repo ↗ Copy URL

Granite 4.1 30B Mxfp8 is an open-source language model by mlx-community. Features: 30b LLM, VRAM: 29.8GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.25.

  8-bit Base model:ibm-granite/granite... Base model:quantized:ibm-grani...   Conversational   Granite   Granite-4.0   Language   Mlx   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/granite-4.1-30b-mxfp8 

Granite 4.1 30B Mxfp8 Parameters and Internals

LLM NameGranite 4.1 30B Mxfp8
Repository 🤗https://huggingface.co/mlx-community/granite-4.1-30b-mxfp8 
Base Model(s)  ibm-granite/granite-4.1-30b   ibm-granite/granite-4.1-30b
Model Size30b
Required VRAM29.8 GB
Updated2026-08-04
Maintainermlx-community
Model Typegranite
Model Files  5.3 GB: 1-of-6   5.4 GB: 2-of-6   5.4 GB: 3-of-6   5.3 GB: 4-of-6   5.4 GB: 5-of-6   3.0 GB: 6-of-6
Model ArchitectureGraniteForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.53.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|pad|>
Vocabulary Size100352
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Granite 4.1 30B Mxfp8

Best Alternatives
Context / RAM
Downloads
Likes
...30B Claude 4.6 Opus Thinking X128K / 58.6 GB481
Granite 4.2 30B128K / 58.2 GB99562
Granite 4.1 30B128K / 57.8 GB20845138
Granite 4.1 30B Base128K / 57.8 GB170527
Granite 4.1 30B Mxfp4128K / 15.3 GB4942
Granite 4.1 30B Nvfp4128K / 16.1 GB3442
Granite 4.1 30B Bf16128K / 57.4 GB831
...6 Opus Thinking Charles Xavier128K / 58.6 GB353
Granite 4.1 30B128K / 57.8 GB560
Unsloth Granite 4.1 30B Mlx128K / 57.4 GB490
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/granite-4.1-30b-mxfp8.