Manedge qwen3 8 b qnn recipe - #2

Closed

xManedge wants to merge 11 commits into

mainfrom

manedge_qwen3_8B_qnn_recipe

Commits on Jul 17, 2026

[Scanner]: Ran scanner and update README.md (#555)

shaahji
and
jambayk
authored
9367c76

Commits on Jul 20, 2026

aitk: add qwen3 qnn (#556)

xieofxie
and
hualxie
authored
8c08fb4
Add mixed quantize configs and eval for gemma4 E2B (#515)

jiafatom
and
Copilot
authored
e17f59e

Commits on Jul 21, 2026

nvidia-nemotron-asr-streaming-multilingual-0.6b: Export FP16 encoder when specifying NvTensorRtRtx execution provider (#530)
p3achyjr
authored
ebd60df

Commits on Jul 22, 2026

Add int8 embedding + mixed int4/int8 decoder quantization to gemma-4-E2B mixed recipe (#558)

jiafatom
and
Copilot
authored
851b284

Commits on Jul 31, 2026

Add Qwen3.5 and Qwen3.6 NvTensorRtRtx recipes (#565)

yen-shi
and
codex
authored
0ed9f84

Commits on Aug 3, 2026

added qwen3 8B recipe to QNN
xManedge
committed
6839f29
added qwen3 8B to qnn recipies
xManedge
committed
84c20ad
Merge branch 'main' into manedge_qwen3_8B_qnn_recipe
xManedge
authored
94ed64f
Potential fix for pull request finding

xManedge
and
Copilot
authored
1daf921
added qwen3 8B to QNN
xManedge
committed
7271d6c