From 1401bd42d436f08d0e75a0a72d2cb341a04fcc74 Mon Sep 17 00:00:00 2001 From: Frank Date: Tue, 1 Sep 2026 01:51:44 -0700 Subject: [PATCH] NPU: swap gemma4-it:e4b for qwen3.8-distilled-heretic:9b --- scripts/frank-default-sightsound.env | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/frank-default-sightsound.env b/scripts/frank-default-sightsound.env index 34ccaf2..980bc7d 100644 --- a/scripts/frank-default-sightsound.env +++ b/scripts/frank-default-sightsound.env @@ -7,7 +7,7 @@ # endpoint trades "uncensored" for "sight + sound". The NPU draws from the # unified RAM pool shared with frank-default-large (iGPU); ~31 GiB was # available there at idle, so a 9.1 GB pack fits with headroom. -FLM_MODEL=gemma4-it:e4b +FLM_MODEL=qwen3.8-distilled-heretic:9b FLM_HOST=0.0.0.0 FLM_PORT=7771 # turbo = max NPU power mode (xrt-smi configure --pmode turbo at serve start).