LLM EXPLORER 57,918 MODELS INDEXED

Medra4b Abliterated by drwlf

By drwlf · 4 downloads
HF Repo ↗ Copy URL

Medra4b Abliterated is an open-source language model by drwlf. Features: 4b LLM, VRAM: 10GB, License: apache-2.0, LLM Explorer Score: 0.19.

Base model:finetune:google/gem... Base model:google/gemma-3-4b-i...   Conversational Dataset:drwlf/medra-thinking-7...   Diagnostic-reasoning   En   Finetuned   Gemma-3   Gemma3   Medical-ai   Region:us   Ro   Safetensors   Sharded   Summarization   Tensorflow
Model Card on HF 🤗: https://huggingface.co/drwlf/Medra4b-abliterated 

Medra4b Abliterated Parameters and Internals

LLM NameMedra4b Abliterated
Repository 🤗https://huggingface.co/drwlf/Medra4b-abliterated 
Base Model(s)  Gemma 3 4B It   google/gemma-3-4b-it
Model Size4b
Required VRAM10 GB
Updated2026-07-27
Maintainerdrwlf
Model Typegemma3
Model Files  5.0 GB: 1-of-2   5.0 GB: 2-of-2
Supported Languagesen ro
Model ArchitectureGemma3ForConditionalGeneration
Licenseapache-2.0
Transformers Version4.52.4
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Torch Data Typebfloat16

Best Alternatives to Medra4b Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Medgemma 4B It Abliterated128K / 6.3 GB136
Gemma 3 Glitter 4B128K / 8.6 GB3347
Fallen Gemma3 4B V1128K / 8.6 GB1318
Gemma 3 4B It0K / 8.6 GB18552621345
Translategemma 4B It0K / 8.6 GB38998793
Nemotron 3 Content Safety0K / 8.6 GB170618
...on Content Safety Reasoning 4B0K / 10 GB869029
Medgemma 1.5 4B It0K / 8.6 GB29369
Gemma 3 4B Pt0K / 8.6 GB72499159
...Gemma 3 4B It Datav3 Only Mask0K / 8.6 GB910
Note: green Score (e.g. "73.2") means that the model is better than drwlf/Medra4b-abliterated.