LLM EXPLORER 60,828 MODELS INDEXED

Recurrentgemma 2B It Bnb 4bit Smashed by PrunaAI

By PrunaAI · 8 downloads
HF Repo ↗ Copy URL

Recurrentgemma 2B It Bnb 4bit Smashed is an open-source language model by PrunaAI. Features: 2b LLM, VRAM: 2.5GB, Quantized, LLM Explorer Score: 0.12.

  4-bit   4bit   Bitsandbytes   Pruna-ai   Quantized   Recurrent gemma   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/PrunaAI/recurrentgemma-2b-it-bnb-4bit-smashed 

Recurrentgemma 2B It Bnb 4bit Smashed Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
Research, Commercial Applications
Considerations:
Efficiency gains should be tested directly in specific use-cases.
Additional Notes 
Configurations detailed in smash_config.json.
Training Details 
Data Sources:
WikiText
Methodology:
Compressed with llm-int8
Hardware Used:
NVIDIA A100-PCIE-40GB
Input Output 
Accepted Modalities:
Text
Performance Tips:
Directly run efficiency evaluations in target use-cases.
LLM NameRecurrentgemma 2B It Bnb 4bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/recurrentgemma-2b-it-bnb-4bit-smashed 
Model Size2b
Required VRAM2.5 GB
Updated2025-09-23
MaintainerPrunaAI
Model Typerecurrent_gemma
Model Files  2.5 GB
Quantization Type4bit
Model ArchitectureRecurrentGemmaForCausalLM
Transformers Version4.40.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Recurrentgemma 2B It Bnb 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
Recurrentgemma 2B It0K / 5.4 GB4026114
Recurrentgemma 2B0K / 10.8 GB212898
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/recurrentgemma-2b-it-bnb-4bit-smashed.