Qwen3.8-27B

· vllm · 256K context · 2 × RTX 3090 in one machine · 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.

29 tok/sdecode

– tok/sprefill

256Kcontext window

Earlier checkSep 16, 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 cyankiwi/Qwen3.8-27B-AWQ-INT4 \
  --revision 63768c10df38c0395e12ef49edac1bd539eaeeea

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:8000 \
  --shm-size 8g \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  vllm/vllm-openai@sha256:0a51ea5b4ae2dc5d81890e5173f54203d2a3ae0cfffe51b8fd2afd4391bfd967 \
  --model cyankiwi/Qwen3.8-27B-AWQ-INT4 \
  --revision 63768c10df38c0395e12ef49edac1bd539eaeeea \
  --served-model-name Qwen3.8-27B \
  --tensor-parallel-size 2 \
  --max-model-len 262144 \
  --max-num-seqs 1 \
  --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.80 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_xml \
  --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 the older check (loads and chats); a full six-check run is pending.

Details

Weights: cyankiwi/Qwen3.8-27B-AWQ-INT4 @ 63768c10df ›
Image: vllm/vllm-openai@sha256:0a51ea5b4ae2dc5d81890e5173f54203d2a3ae0cfffe51b8fd2afd4391bfd967
Launch: vllm-qwen3.8-27b-int4-w4a16-256k ›
Recipe file: registry/recipes/nvidia/rtx-3090-24gb/qwen3.8-27b.vllm.256k.2x.json ›
Model released: Aug 5, 2026
Tested: earlier acceptance