LLM EXPLORER 61,249 MODELS INDEXED

Medgemma 27B Text It GPTQ 4bit by HarshBhanushali7705

By HarshBhanushali7705 · 648 downloads

Medgemma 27B Text It GPTQ 4bit is an open-source language model by HarshBhanushali7705. Features: 27b LLM, VRAM: 16.2GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.27.

  4-bit   4bit Base model:google/medgemma-27b... Base model:quantized:google/me...   Conversational   Doi:10.57967/hf/9589   Gemma-3   Gemma3 text   Gptq   Marlin   Medgemma   Medical   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm

Medgemma 27B Text It GPTQ 4bit Parameters and Internals

LLM NameMedgemma 27B Text It GPTQ 4bit
Repository πŸ€—https://huggingface.co/HarshBhanushali7705/medgemma-27b-text-it-GPTQ-4bit 
Base Model(s)  google/medgemma-27b-text-it   google/medgemma-27b-text-it
Model Size27b
Required VRAM16.2 GB
Updated2026-08-01
MaintainerHarshBhanushali7705
Model Typegemma3_text
Model Files  4.3 GB: 1-of-4   4.3 GB: 2-of-4   4.3 GB: 3-of-4   3.3 GB: 4-of-4
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureGemma3ForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version5.13.0
Tokenizer ClassGemmaTokenizerFast
Padding Token<pad>
Vocabulary Size262144

Best Alternatives to Medgemma 27B Text It GPTQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Medgemma 27B Text It Bnb 4bit128K / 16.1 GB11263
...a 27B Text It Unsloth Bnb 4bit128K / 16.6 GB10507
Medgemma 27B Text It 4bit128K / 16 GB2343
Medgemma 27B Text It 8bit128K / 30.3 GB1292
Gemma 3 27B It Qat Abliterated128K / 108.9 GB2320
Fanar 2 27B Instruct128K / 54.4 GB1091711
Medgemma 27B Text It GGUF128K / 6.5 GB428873
YanoljaNEXT Rosetta 27B 2511128K / 57.2 GB3335
Medgemma 27B Text Heretic Med128K / 54.4 GB508
Medgemma 27B Text It128K / 54.4 GB12178
Note: green Score (e.g. "73.2") means that the model is better than HarshBhanushali7705/medgemma-27b-text-it-GPTQ-4bit.