empirischtech/DeepSeek-R1-Distill-Qwen-32B-gptq-4bit
https://huggingface.co/empirischtech/DeepSeek-R1-Distill-Qwen-32B-gptq-4bitIdleby empirischtech11316updated 6 months ago
A domain-optimized reasoning model built on DeepSeek-R1-Distill-Qwen-32B, refined through a multi-stage pipeline of GPTQ quantization-aware training and QLoRA fine-tuning. Achieves 84% on MedQA — within 4 points of GPT-4o — in a ~20GB package that fits on a single L40/L40s GPU.
Sourced from
- HuggingFace — empirischtech/DeepSeek-R1-Distill-Qwen-32B-gptq-4bit
Related resources
fableforge-ai/NEXUS-Medical
by fableforge-ai> NEXUS domain specialist for medical Q&A and clinical reasoning — lightweight & uncensored.
HarshBhanushali7705/medgemma-27b-text-it-GPTQ-4bit
by HarshBhanushali7705This 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.
Active3463 months ago
Idle91 year ago