Granite 3.2 8B Instruct by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  Granite 3.2 8B Instruct   URL Share it on

  Arxiv:0000.00000   Autotrain compatible Base model:finetune:ibm-granit... Base model:ibm-granite/granite...   Conversational   Ganite   Granite   Granite-3.2   Instruct   Language   Region:us   Safetensors   Sharded   Tensorflow

Granite 3.2 8B Instruct Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Granite 3.2 8B Instruct (unsloth/granite-3.2-8b-instruct)

Granite 3.2 8B Instruct Parameters and Internals

LLM NameGranite 3.2 8B Instruct
Repository ๐Ÿค—https://huggingface.co/unsloth/granite-3.2-8b-instruct 
Base Model(s)  ibm-granite/granite-3.2-8b-instruct   ibm-granite/granite-3.2-8b-instruct
Model Size8b
Required VRAM21.5 GB
Updated2025-04-23
Maintainerunsloth
Model Typegranite
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   5.0 GB: 1-of-4   0.1 GB: 2-of-2   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.4 GB: 4-of-4
Model ArchitectureGraniteForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.49.0
Tokenizer ClassGPT2Tokenizer
Padding Token<fim_pad>
Vocabulary Size49155
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Granite 3.2 8B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Granite 3.1 8B Instruct128K / 16.4 GB52535156
Granite 3.2 8B Instruct128K / 16.4 GB4866781
Granite 3.3 8B Instruct128K / 16.4 GB851759
...ranite 3.2 8B Instruct Preview128K / 16.4 GB54069
Granite 3.1 8B Reasoning128K / 16.4 GB171
Granite 3.0 8B Instruct4K / 16.4 GB20098199
...te 3.0 8B Lora Intrinsics V0.14K / 32.8 GB72
...te 3.0 8B Instruct Abliterated4K /  GB22
Granite 3.3 8B Instruct Fp16128K / 16.4 GB332
...anite 3.2 8B Instruct Bnb 4bit128K / 4.5 GB2593
Note: green Score (e.g. "73.2") means that the model is better than unsloth/granite-3.2-8b-instruct.

Rank the Granite 3.2 8B Instruct Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 46599 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227