Field	Value
Base model	google/gemma-4-31B-it
Published artifact	positron-ai/google_gemma-4-31B-it-ingest-best-gptq
Quantization method	GPTQ
Quantization format	gptq
Source precision	n/a
Target runtime	n/a
Hardware target	n/a
Release date	2026-09-02
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 7.1.0, 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-4-31B-it. The original model license and usage restrictions continue to apply.

positron-ai/google_gemma-4-31B-it-ingest-best-gptq

Positron AI Quantized Build

Recommended Use

Artifact Summary

Quantization Details

Evaluation

Provenance

positron-ai/
google_gemma-4-31B-it-ingest-best-gptq