Qwen3.8-27B

FP8 · sglang · 96K context · RTX 6000 Ada · 48 GB

Alibaba's 27B dense model from August 2026, and the strongest model that fits one consumer card. It thinks before it answers, calls tools reliably and reads images, which makes it the default for coding agents and long projects.

23 tok/sdecode

1,822 tok/sprefill

96Kcontext 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/Qwen3.8-27B-FP8 \
  --revision 017b9c7af6b5689d5dd426a76e0bc077eb5ca20a \
  --local-dir ~/models/Qwen3.8-27B-FP8-017b9c7a

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:30000 \
  --shm-size 16g \
  -v ~/models/Qwen3.8-27B-FP8-017b9c7a:/models/Qwen3.8-27B-FP8-017b9c7a:ro \
  --entrypoint python3 \
  lmsysorg/sglang:v0.5.20-cu130-runtime@sha256:00b02004501e402332827ffd5343a225a8960d99adc990b37d6f31085b8f6800 \
  -m sglang.launch_server \
  --model-path /models/Qwen3.8-27B-FP8-017b9c7a \
  --served-model-name Qwen3.8-27B-FP8-017b9c7a \
  --host 0.0.0.0 \
  --port 30000 \
  --trust-remote-code \
  --context-length 98304 \
  --max-running-requests 1 \
  --mem-fraction-static 0.9 \
  --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/Qwen3.8-27B-FP8 @ 017b9c7af6 ›
Image: lmsysorg/sglang:v0.5.20-cu130-runtime@sha256:00b02004501e402332827ffd5343a225a8960d99adc990b37d6f31085b8f6800
Engine profile: sglang ›
Recipe file: registry/recipes/nvidia/rtx-6000-ada-48gb/qwen3.8-27b.sglang.96k.json ›
Model released: Aug 5, 2026
Tested: vast, RTX 6000Ada