Qwen3.8-27B

· llama.cpp · 128K context · Radeon 8060S · 64 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.

21 tok/sdecode

70 tok/sprefill

128Kcontext window

Tested on this cardOct 20, 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 unsloth/Qwen3.8-27B-GGUF Qwen3.8-27B-IQ4_XS.gguf,mmproj-F16.gguf \
  --revision f975863083b62f54a5e6fac11671c750c2bbc59c \
  --local-dir ~/models/Qwen3.8-27B-GGUF-f9758630

2 Start the server

docker run --rm \
  --device /dev/dri \
  -p 8000:8080 \
  --shm-size 8g \
  -v ~/models/Qwen3.8-27B-GGUF-f9758630:/models:ro \
  ghcr.io/ggml-org/llama.cpp@sha256:1086b8815273e566bc0f549bac1d6d2dc469e6409a952cca3f502e53d72877e7 \
  -m /models/Qwen3.8-27B-IQ4_XS.gguf \
  --mmproj /models/mmproj-F16.gguf \
  --alias Qwen3.8-27B-GGUF \
  --host 0.0.0.0 \
  --port 8080 \
  --ctx-size 131072 \
  --n-gpu-layers 999 \
  --parallel 1 \
  --spec-type draft-mtp \
  --spec-draft-n-max 2 \
  --jinja \
  --reasoning-format deepseek \
  --reasoning-effort medium \
  --temp 1.0 \
  --top-p 0.95 \
  --top-k 20 \
  --metrics

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 AMD Radeon 8060S (owner: Omarchy, Ryzen AI Max+ 392 64GB, RADV GFX1151) on Oct 20, 2026.

Details

Weights: unsloth/Qwen3.8-27B-GGUF @ f975863083 ›
Image: ghcr.io/ggml-org/llama.cpp@sha256:1086b8815273e566bc0f549bac1d6d2dc469e6409a952cca3f502e53d72877e7
Launch: llama.cpp-vulkan-qwen3.8-27b-iq4-xs-mtp-128k ›
Recipe file: registry/recipes/amd/radeon-8060s-64gb/qwen3.8-27b.llama.cpp.128k.json ›
Model released: Aug 5, 2026
Tested: owner, AMD Radeon 8060S (owner: Omarchy, Ryzen AI Max+ 392 64GB, RADV GFX1151)