Qwen3.5-9B

· flm · 32K context · Ryzen AI NPU (Krackan) · 16 GB

Alibaba's 9B model from February 2026: small enough for an 8 GB card, with a 64K–128K window. It thinks, calls tools and stays quick on modest hardware.

5 tok/sdecode

– tok/sprefill

32Kcontext window

Earlier checkSep 17, 2026

Run it

Follow the steps below to download and run this recipe. Omarchy Local AI lists the recipes it can launch on your hardware. The server then answers on http://localhost:52626/v1.

1 Install

# https://github.com/FastFlowLM/FastFlowLM

2 Start the server
```
flm serve qwen3.5:9b --port 52626
```

What it passed

✓ loadLoads and serves within an hour

✓ chatAnswers a plain question and stops on its own

– reasoningThinks separately and gets 17 × 23 right

– toolsCalls a tool with the right arguments and uses the result

– contextRecalls a code buried in a prompt that fills 85% of the window

– speedDecodes at 15 tok/s or more

Passed the older check (loads and chats); a full six-check run is pending.

Details

Weights: inside the image
Image: none: a program on the host
Launch: flm-qwen3.5-9b-q4nx-32k ›
Recipe file: registry/recipes/amd/xdna2-krackan-16gb/qwen3.5-9b.flm.32k.json ›
Model released: Feb 26, 2026
Tested: earlier acceptance