Qwen3.8-27B

NVFP4 · sglang · 128K context · RTX PRO 6000 Blackwell · 96 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.

88 tok/sdecode

– tok/sprefill

128Kcontext window

Earlier checkSep 22, 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 RadixArk/Qwen3.8-27B-NVFP4 \
  --revision 319f741cce68d7914884900c138a1fbb70a42f30

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:30000 \
  --shm-size 16g \
  -e HF_HOME=/root/.cache/huggingface \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  --entrypoint /opt/sglang/bin/python \
  lmsysorg/sglang:dev-cu13@sha256:6cd4635214f279e0a43019f88e3120d407567640a58aa7dcc0085e3d91402cc4 \
  -m sglang.launch_server \
  --model-path RadixArk/Qwen3.8-27B-NVFP4 \
  --revision 319f741cce68d7914884900c138a1fbb70a42f30 \
  --tp 1 \
  --speculative-algo NEXTN \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --host 0.0.0.0 \
  --port 30000 \
  --context-length 131072 \
  --mem-fraction-static 0.87 \
  --attention-backend flashinfer \
  --kv-cache-dtype fp8_e4m3 \
  --max-running-requests 4 \
  --cuda-graph-max-bs-decode 4 \
  --enable-cache-report \
  --trust-remote-code \
  --reasoning-parser qwen3 \
  --tool-call-parser qwen3_coder

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: RadixArk/Qwen3.8-27B-NVFP4 @ 319f741cce ›
Image: lmsysorg/sglang:dev-cu13@sha256:6cd4635214f279e0a43019f88e3120d407567640a58aa7dcc0085e3d91402cc4
Launch: sglang-qwen3.8-27b-nvfp4-128k ›
Recipe file: registry/recipes/nvidia/rtx-pro-6000-blackwell-96gb/qwen3.8-27b.sglang.128k.json ›
Model released: Aug 5, 2026
Tested: earlier acceptance