Qwen3.6-35B-A3B

FP8 · sglang · 128K context · RTX 6000 Ada · 48 GB

Qwen3.6's 35B mixture-of-experts model with 3B active parameters.

141 tok/sdecode

6,641 tok/sprefill

128Kcontext window

Tested on this cardSep 26, 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:8000/v1.

1 Download the weights

hf download Qwen/Qwen3.6-35B-A3B-FP8 \
  --revision 95a723d08a9490559dae23d0cff1d9466213d989 \
  --local-dir ~/models/Qwen3.6-35B-A3B-FP8-95a723d0

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:30000 \
  --shm-size 16g \
  -v ~/models/Qwen3.6-35B-A3B-FP8-95a723d0:/models/Qwen3.6-35B-A3B-FP8-95a723d0:ro \
  --entrypoint python3 \
  lmsysorg/sglang:v0.5.20-cu130-runtime@sha256:00b02004501e402332827ffd5343a225a8960d99adc990b37d6f31085b8f6800 \
  -m sglang.launch_server \
  --model-path /models/Qwen3.6-35B-A3B-FP8-95a723d0 \
  --served-model-name Qwen3.6-35B-A3B-FP8-95a723d0 \
  --host 0.0.0.0 \
  --port 30000 \
  --trust-remote-code \
  --context-length 131072 \
  --max-running-requests 1 \
  --mem-fraction-static 0.85 \
  --kv-cache-dtype auto \
  --tool-call-parser qwen3_coder \
  --reasoning-parser qwen3

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 all six checks on a real RTX 6000Ada on Sep 26, 2026.

Details

Weights: Qwen/Qwen3.6-35B-A3B-FP8 @ 95a723d08a ›
Image: lmsysorg/sglang:v0.5.20-cu130-runtime@sha256:00b02004501e402332827ffd5343a225a8960d99adc990b37d6f31085b8f6800
Engine profile: sglang ›
Recipe file: registry/recipes/nvidia/rtx-6000-ada-48gb/qwen3.6-35b-a3b.sglang.128k.json ›
Model released: Apr 15, 2026
Tested: vast, RTX 6000Ada