gaunernst / image-text-to-text updated 1 year ago

gemma-3-27b-it-int4-awq

Name: gemma-3-27b-it-int4-awq
Author: gaunernst

This is the QAT INT4 Flax checkpoint (from Kaggle) converted to HF+AWQ format for ease of use. AWQ was NOT used for quantization. You can find the conversion script convertflax.py in this model repo.

Params

27.4 B

Context

—

Downloads 30d

1.2 M

Likes

Commercial use: conditional · gemma Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.2 M987 K

Jul 28Jul 31Aug 3Aug 6

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	18.5 GB	24.9 GB	❌ Won’t fit

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

Specifications

Architecture: Gemma3ForConditionalGeneration
Parameters: 27.4 B
Tensor type: I32
Licence: gemma
First seen on the Hub: 2025-03-21
Base model: gemma-3-27b-it
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base gemma-3-27b-it google 857 K

Compare with

gemma-4-31B-it 11.9 M gemma-4-26B-A4B-it 11.7 M Qwen3.6-35B-A3B-FP8 8.9 M Qwen2.5-VL-3B-Instruct 8.2 M Qwen3.6-27B-FP8 7.8 M Qwen3.6-27B 7.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB