Field	Value
Base model	Qwen/Qwen2.5-32B-Instruct
Published artifact	positron-ai/Qwen_Qwen2.5-32B-Instruct-ingest-best-gptq
Quantization method	GPTQ
Quantization format	gptq
Source precision	n/a
Target runtime	n/a
Hardware target	n/a
Release date	2026-08-25
License	other

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	256
Calibration sequence length	2048
MoE experts per token	n/a
Quantization toolchain	GPTQModel 5.8.0, transformers 4.57.6, torch 2.9.1, CUDA 12.8

Validation Results

Metric	Result	Reference	Notes
Mean KL-divergence	n/a	n/a	Not measured for this release
P95 KL-divergence	n/a	n/a	Not measured for this release
Top-1 agreement	n/a	n/a	Not measured for this release
Perplexity / NLL delta	n/a	n/a	Not measured for this release
MMLU mean	0.6726	Qwen/Qwen2.5-32B-Instruct	MMLU at 10% coverage

KL-divergence has not been measured for this release; the metrics above will be populated when validation completes.

This artifact was produced by Positron AI from Qwen/Qwen2.5-32B-Instruct. The original model license and usage restrictions continue to apply.