Quantized Granite 4bit 3B Code Instruct by RyanJT

 ยป  All LLMs  ยป  RyanJT  ยป  Quantized Granite 4bit 3B Code Instruct   URL Share it on

  4-bit   4bit   Autotrain compatible   Bitsandbytes   Conversational   Endpoints compatible   Instruct   Llama   Quantized   Region:us   Safetensors

Quantized Granite 4bit 3B Code Instruct Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Quantized Granite 4bit 3B Code Instruct Parameters and Internals

LLM NameQuantized Granite 4bit 3B Code Instruct
Repository ๐Ÿค—https://huggingface.co/RyanJT/quantized-granite-4bit-3b-code-instruct 
Model Size3b
Required VRAM2 GB
Updated2025-06-09
MaintainerRyanJT
Model Typellama
Instruction-BasedYes
Model Files  2.0 GB
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.42.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size49152
Torch Data Typefloat16
Quantized Granite 4bit 3B Code Instruct (RyanJT/quantized-granite-4bit-3b-code-instruct)

Quantized Models of the Quantized Granite 4bit 3B Code Instruct

Model
Likes
Downloads
VRAM
Trained Quant 4bit050 GB

Best Alternatives to Quantized Granite 4bit 3B Code Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...2 3B Instruct Unsloth Bnb 4bit128K / 2.4 GB14015010
Llama32 3B En Emo 2000 Stp128K / 2.2 GB380
Llama32 3B En Emo 300 Stp128K / 2.2 GB290
Llama32 3B En Emo 1000 Stp128K / 2.2 GB210
Llama32 3B En Emo 5000 Stp128K / 2.2 GB300
ReasoningCore 3B 0128K / 6.5 GB432
...ngCore 3B Instruct R01 Reflect128K / 6.5 GB01
....1 Pretrained Unsloth Bnb 4bit128K / 2.5 GB34113
...a 3.2 3B Instruct T Base Merge128K / 6.5 GB860
Security Llama3.2 3B128K / 6.5 GB170
Note: green Score (e.g. "73.2") means that the model is better than RyanJT/quantized-granite-4bit-3b-code-instruct.

Rank the Quantized Granite 4bit 3B Code 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? 48023 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124