Granite 4.1 8B 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Granite 4.1 8B 8bit   URL Share it on

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.

  8-bit   8bit Base model:ibm-granite/granite... Base model:quantized:ibm-grani...   Conversational   Granite   Granite-4.1   Language   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Granite 4.1 8B 8bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Granite 4.1 8B 8bit Parameters and Internals

LLM NameGranite 4.1 8B 8bit
Repository 🤗https://huggingface.co/mlx-community/granite-4.1-8b-8bit 
Base Model(s)  ibm-granite/granite-4.1-8b   ibm-granite/granite-4.1-8b
Model Size8b
Required VRAM9.4 GB
Updated2026-06-21
Maintainermlx-community
Model Typegranite
Model Files  5.3 GB: 1-of-2   4.1 GB: 2-of-2
Quantization Type8bit
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 8B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...anite 3.2 8B Instruct Bnb 4bit128K / 4.5 GB5533
Granite 3.3 8B Instruct Fp16128K / 16.4 GB473
Granite 3.3 8B Instruct 8bit128K / 8.6 GB362
Granite 4.1 8B128K / 17.6 GB21803161
Granite 3.1 8B Instruct128K / 16.4 GB73170168
Granite 4.1 8B Base128K / 16.8 GB1863025
Granite Guardian 4.1 8B128K / 16.8 GB1000128
Granite 4.1 8B Fp8128K / 9.7 GB1176812
Granite 3.1 8B Reasoning128K / 16.4 GB41
Granite 3.1 8B Instruct128K / 16.4 GB1241
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/granite-4.1-8b-8bit.

Rank the Granite 4.1 8B 8bit 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 54565 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a