HarshBhanushali7705/medgemma-27b-text-it-GPTQ-4bit
https://huggingface.co/HarshBhanushali7705/medgemma-27b-text-it-GPTQ-4bitThis repository contains a 4-bit GPTQ quantized version of google/medgemma-27b-text-it, optimized for high-throughput inference using vLLM and the Marlin kernel.
Sourced from
- HuggingFace — HarshBhanushali7705/medgemma-27b-text-it-GPTQ-4bit
Related resources
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.
mlx-community/medgemma-27b-text-it-bf16
by mlx-communityThis model mlx-community/medgemma-27b-text-it-bf16 was converted to MLX format from google/medgemma-27b-text-it using mlx-lm version 0.25.1.
> [!NOTE] > Inspired by the thought of: what if you could speak to an offline medical assistant that doesn't decline to answer some of your questions?
iti-visual-analytics/GRamma-12B
by iti-visual-analyticsGRamma-12B is a 12-billion-parameter instruction-tuned language model specialized for the Greek medical domain. It is built on top of Gemma 3 12B Instruct and adapted through parameter-efficient fine-tuning on a collection of Greek and bilingual medical question-answering data.
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.