bbarn4 / text-generation Open weights updated 6 months ago

medgemma-27b-text-it-GPTQ

Name: medgemma-27b-text-it-GPTQ
Author: bbarn4

This is a 4-bit GPTQ quantization of google/medgemma-27b-text-it, the text-only variant of Google's MedGemma optimized for medical text reasoning.

Params

4.8 B

Context

131,072

Downloads 30d

202 K

Likes

Licence: other Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 52 days

▲ 0 in the last 30 days (0.0%)

304 K188 K

Sep 4Sep 21Oct 8Oct 25

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	i32	16.0 GB	18.8 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 128K ctx	16.0 GB	29.7 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/medgemma-27b-text-it-gptq
{
  "hf_id": "bbarn4/medgemma-27b-text-it-GPTQ",
  "params_b": 4.81,
  "context_length": 131072,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 202049,
  "vram_estimates": [
    { "quant": "i32", "gb": 18.8 }
  ],
  "updated_at": "2026-09-04T01:00:23Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Gemma3ForCausalLM
Parameters: 4.8 B
Tensor type: I32
Context length: 131,072
Vocabulary: 262,144
Layers / heads: 62 / 32
Licence: other
First seen on the Hub: 2026-04-03
Training datasets: undisclosed
Added to our catalog: 2026-09-04

Compare with any text-generation model

Popular comparisons

Qwen3-4B 11.4 M Qwen3-14B 10.0 M Qwen3-8B 8.2 M Qwen2.5-7B-Instruct 6.1 M Llama-3.1-8B-Instruct 4.9 M Qwen2.5-3B-Instruct 3.7 M