LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Granite 4.0 H Small by unsloth

 »  All LLMs  »  unsloth  »  Granite 4.0 H Small   URL Share it on

  969   

Granite 4.0 H Small is an open-source language model by unsloth. Features: 32.2b LLM, VRAM: 64.4GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.25.

  Arxiv:0000.00000 Base model:finetune:ibm-granit... Base model:ibm-granite/granite...   Conversational   Endpoints compatible   Granite-4.0   Granitemoehybrid   Language   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/granite-4.0-h-small 

Granite 4.0 H Small Benchmarks

LLME Score: 0.24884
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Granite 4.0 H Small (unsloth/granite-4.0-h-small)
🌟 Advertise your project 🚀

Granite 4.0 H Small Parameters and Internals

LLM NameGranite 4.0 H Small
Repository 🤗https://huggingface.co/unsloth/granite-4.0-h-small 
Base Model(s)  ibm-granite/granite-4.0-h-small   ibm-granite/granite-4.0-h-small
Model Size32.2b
Required VRAM64.4 GB
Updated2026-03-28
Maintainerunsloth
Model Typegranitemoehybrid
Model Files  4.9 GB: 1-of-14   4.8 GB: 2-of-14   4.7 GB: 3-of-14   4.8 GB: 4-of-14   4.8 GB: 5-of-14   4.7 GB: 6-of-14   4.8 GB: 7-of-14   4.8 GB: 8-of-14   4.7 GB: 9-of-14   4.8 GB: 10-of-14   4.8 GB: 11-of-14   4.8 GB: 12-of-14   4.7 GB: 13-of-14   2.3 GB: 14-of-14
Model ArchitectureGraniteMoeHybridForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.57.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|pad|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Granite 4.0 H Small

Best Alternatives
Context / RAM
Downloads
Likes
...e 4.0 H Small Unsloth Bnb 4bit128K / 58.1 GB553

Rank the Granite 4.0 H Small 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? 52221 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
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
  Support LLM Explorer