Qwen3.8-27B

· llama.cpp · 8K context · 2 × Radeon PRO W7800 in one machine · 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.

41 tok/sdecode

– tok/sprefill

8Kcontext window

Earlier checkSep 7, 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 orcarouter/Qwen3.8-27B-Uncensored-GGUF \
  --revision a855f377abf5cbda99a278414466743f427e97c8

2 Write the server config

cat > qwen3.8-27b.llama.cpp.8k.2x.yml <<'EOF'
{
  "llamacpp": {
    "backend": "rocm",
    "prefer_system": false,
    "rocm_args": "--flash-attn on -b 2048 -ub 512 -sm tensor -ts 0.5,0.5 --spec-type draft-mtp --spec-draft-n-max 3",
    "rocm_bin": "b1323"
  },
  "rocm_channel": "nightly"
}
EOF

3 Start the server

docker run --rm \
  --device /dev/kfd --device /dev/dri \
  -p 8000:13305 \
  --ipc host \
  --shm-size 16g \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -v $PWD/qwen3.8-27b.llama.cpp.8k.2x.yml:/opt/lemonade/.config/lemonade/config.json:ro \
  --entrypoint /opt/lemonade/lemond \
  ghcr.io/lemonade-sdk/lemonade-server:v11.9.0@sha256:7c780707cd695392a8680f557c7c1d55521383a71b1c4c5a9d9e6a226a1bee91 \
  --host 0.0.0.0

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: orcarouter/Qwen3.8-27B-Uncensored-GGUF @ a855f377ab ›
Image: ghcr.io/lemonade-sdk/lemonade-server:v11.9.0@sha256:7c780707cd695392a8680f557c7c1d55521383a71b1c4c5a9d9e6a226a1bee91
Launch: llama.cpp-qwen3.8-27b-q6-k-8k-v2 ›
Recipe file: registry/recipes/amd/radeon-pro-w7800-48gb/qwen3.8-27b.llama.cpp.8k.2x.json ›
Model released: Aug 5, 2026
Tested: earlier acceptance