Modelpublic

positron-ai/google_gemma-4-26B-A4B-it-ingest-best-gptq

sourceHugging Faceapache-2.0updated 26d agoView on Hugging Face

0likes530downloads

Model Card

Positron AI Quantized Build

This repository contains a Positron AI quantized build of google/gemma-4-26B-A4B-it for inference.

Recommended Use

Use this artifact when you need a GPTQ 4-bit build of google/gemma-4-26B-A4B-it built by Positron AI.

For general-purpose GPU inference, compare against the original model and other quantized formats before deployment.

Artifact Summary

Field	Value
Base model	google/gemma-4-26B-A4B-it
Published artifact	positron-ai/google_gemma-4-26B-A4B-it-ingest-best-gptq
Quantization method	GPTQ
Quantization format	gptq
Source precision	n/a
Target runtime	n/a
Hardware target	n/a
Release date	2026-09-01
License	apache-2.0

Quantization Details

Field	Value
Weight precision	4-bit
Activation precision	not quantized
Bits	4
Group size	64
Symmetric quantization	true
Activation ordering / desc_act	false
Damp percent	0.05
Calibration dataset	Mixed-domain calibration set
Calibration samples	128
Calibration sequence length	4096
MoE experts per token	n/a
Quantization toolchain	GPTQModel 7.2.0, transformers 5.11.0, torch 2.9.1, CUDA 12.8

Evaluation

This card intentionally reports no performance or quality metrics (no KL-divergence, accuracy, or perplexity figures). Validation results are tracked internally by Positron AI.

Provenance

This artifact was produced by Positron AI from google/gemma-4-26B-A4B-it. The original model license and usage restrictions continue to apply.