LLM EXPLORER 57,918 MODELS INDEXED

Medgemma 4B It Bnb 4bit by unsloth

By unsloth · 768 downloads
HF Repo ↗ Copy URL

Medgemma 4B It Bnb 4bit is an open-source language model by unsloth. Features: 4b LLM, VRAM: 3.2GB, License: other, Quantized, LLM Explorer Score: 0.19.

  Arxiv:2009.13081   Arxiv:2102.09542   Arxiv:2106.14463   Arxiv:2303.15343   Arxiv:2405.03162   Arxiv:2411.15640   Arxiv:2412.03555   Arxiv:2501.18362   Arxiv:2501.19393   4-bit   4bit Base model:google/medgemma-4b-... Base model:quantized:google/me...   Bitsandbytes   Chest-x-ray   Clinical-reasoning   Conversational   Dermatology   Endpoints compatible   Gemma3   Image-text-to-text   Medical   Ophthalmology   Pathology   Quantized   Radiology   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/medgemma-4b-it-bnb-4bit 

Medgemma 4B It Bnb 4bit Parameters and Internals

LLM NameMedgemma 4B It Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/medgemma-4b-it-bnb-4bit 
Base Model(s)  google/medgemma-4b-it   google/medgemma-4b-it
Model Size4b
Required VRAM3.2 GB
Updated2026-08-10
Maintainerunsloth
Model Typegemma3
Model Files  3.2 GB
Quantization Type4bit
Model ArchitectureGemma3ForConditionalGeneration
Licenseother
Model Max Length131072
Transformers Version4.51.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Torch Data Typebfloat16

Best Alternatives to Medgemma 4B It Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 3 4B It Unsloth Bnb 4bit0K / 4.6 GB2345726
Gemma 3 4B It Bnb 4bit0K / 3.2 GB1344312
...a 3 4B It Qat Q4 0 Unquantized0K / 8.6 GB101611
Gemma 3 4B It Qat0K / 8.6 GB581
...4B It 4bit Immersive Translate0K / 2.2 GB133810
Translategemma 4B It 4bit0K / 2.2 GB16199
Medgemma 1.5 4B It Bnb 4bit0K / 3.8 GB4486
Translategemma 4B It 8bit0K / 4.1 GB4405
Medgemma 1.5 4B It 4bit0K / 3.4 GB4603
...mma 1.5 4B It Unsloth Bnb 4bit0K / 3.8 GB3063
Note: green Score (e.g. "73.2") means that the model is better than unsloth/medgemma-4b-it-bnb-4bit.