gemma2-9b · fp8 · W8A16 · calibrated on mixed

Post-training quantization with NVIDIA ModelOpt (FP8_DEFAULT_CFG); activation quantizers were disabled after calibration, so the exported model is weight-only.

base model google/gemma-2-9b-it
base dtype float16
mode W8A16 — FP8 weights (E4M3, per-tensor scale), activations FP16
calibration calib3_mixed.txt, 512 samples, 512 tokens, variety mixed
calibration reaches weights no — see below
weight MSE 3.163557e-08
weight quantizers 294
environment torch 2.8.0+cu128 · transformers 4.57.6 · modelopt 0.46.0

Weight scales here are computed data-free from the weights themselves. With activations left in FP16 there is nothing for the calibration text to affect, so this checkpoint would be identical whatever text were used. It is a control the AWQ variants are measured against.

The checkpoint stores plain quantized weights; nothing inside it records the weight-only mode. That lives in the repo name and calib_stats.json only.

Not loadable by plain transformersconfig.json declares quantization type modelopt.

vllm serve Azzam15/gemma2-9b-fp8-w8a16-mixed --quantization modelopt

Not comparable to a W4A4 checkpoint: the gap between them is partly precision and partly which tensors were quantized at all.

Downloads last month
9
Safetensors
Model size
9B params
Tensor type
F16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Azzam15/gemma2-9b-fp8-w8a16-mixed

Quantized
(181)
this model