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 3B Code Instruct GGUF by SanctumAI

 »  All LLMs  »  SanctumAI  »  Granite 3B Code Instruct GGUF   URL Share it on

  1207   

Granite 3B Code Instruct GGUF is an open-source language model by SanctumAI. Features: 3b LLM, VRAM: 1.3GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.15.

  Arxiv:2405.04324 Base model:ibm-granite/granite... Base model:quantized:ibm-grani...   Code   Conversational   Dataset:bigcode/commitpackft Dataset:bugdaryan/sql-create-c... Dataset:garage-baind/open-plat... Dataset:glaive-function-callin... Dataset:glaiveai/glaive-code-a...   Dataset:meta-math/metamathqa   Dataset:nvidia/helpsteer   Dataset:tiger-lab/mathinstruct   Endpoints compatible   Gguf   Granite   Ibm-granite-code   Instruct   Model-index   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/SanctumAI/granite-3b-code-instruct-GGUF 

Granite 3B Code Instruct GGUF Benchmarks

LLME Score: 0.14912
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Granite 3B Code Instruct GGUF (SanctumAI/granite-3b-code-instruct-GGUF)
🌟 Advertise your project 🚀

Granite 3B Code Instruct GGUF Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model was fine-tuned on a combination of permissively licensed instruction data to enhance instruction following capabilities, including logical reasoning and problem-solving skills.
LLM NameGranite 3B Code Instruct GGUF
Repository 🤗https://huggingface.co/SanctumAI/granite-3b-code-instruct-GGUF 
Base Model(s)  Granite 3B Code Base   ibm-granite/granite-3b-code-base
Model Size3b
Required VRAM1.3 GB
Updated2026-04-12
MaintainerSanctumAI
Model Typeibm-granite-code
Instruction-BasedYes
Model Files  1.3 GB   1.9 GB   1.7 GB   1.6 GB   2.0 GB   2.2 GB   2.1 GB   2.1 GB   2.0 GB   2.4 GB   2.6 GB   2.5 GB   2.5 GB   2.4 GB   2.9 GB   3.7 GB   7.0 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Granite 3B Code Instruct GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Llama32 3B En Emo V3128K / 2 GB120
Llama 3.2 3B VanRossum0K / 6.5 GB1050
Legal Llama3 Lora Model0K / 3.4 GB100
...ma Doctor 3.2 3B Instruct GGUF0K / 2 GB19057
MedQwen3B Reasoner0K / 6.2 GB21013
...a Song Stream 3B Instruct GGUF0K / 2 GB2956
... Sentient 3.2 3B Instruct GGUF0K / 2 GB2098
QwQ LCoT 3B Instruct GGUF0K / 1.9 GB277
...ma Magpie 3.2 3B Instruct GGUF0K / 2 GB572
Llama 3.2 3B Instruct GGUF0K / 2 GB532
Note: green Score (e.g. "73.2") means that the model is better than SanctumAI/granite-3b-code-instruct-GGUF.

Rank the Granite 3B Code Instruct GGUF 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? 53407 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