Qwen3.8-27B

· llama.cpp · 128K context · Arc Pro B65 · 32 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.

24 tok/sdecode

575 tok/sprefill

128Kcontext window

Tested on this cardOct 14, 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 lmstudio-community/Qwen3.8-27B-GGUF Qwen3.8-27B-Q4_K_M.gguf \
  --revision 5a7da681f60570ab5b439a587e912d2e5eddb582 \
  --local-dir ~/models/Qwen3.8-27B-GGUF-5a7da681

2 Start the server

docker run --rm \
  --device /dev/dri \
  -p 8000:8080 \
  --shm-size 8g \
  -e ONEAPI_DEVICE_SELECTOR=level_zero:0 \
  -e UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1 \
  -v ~/models/Qwen3.8-27B-GGUF-5a7da681:/models:ro \
  ghcr.io/ggml-org/llama.cpp@sha256:86b37d266ce85b485127adea68c9dc6d04d0ec9a64b0979844d5bbd8d66c53c5 \
  -m /models/Qwen3.8-27B-Q4_K_M.gguf \
  --alias Qwen3.8-27B-GGUF \
  --host 0.0.0.0 \
  --port 8080 \
  --ctx-size 131072 \
  --n-gpu-layers 999 \
  --parallel 1 \
  --flash-attn on \
  --batch-size 2048 \
  --ubatch-size 2048 \
  --jinja \
  --reasoning-format deepseek \
  --no-mmproj \
  --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 Intel Arc Pro B65 32 GB (ASRock Creator; owner: Ryzen 7 5700X, PCIe 4.0 x4) on Oct 14, 2026.

Details

Weights: lmstudio-community/Qwen3.8-27B-GGUF @ 5a7da681f6 ›
Image: ghcr.io/ggml-org/llama.cpp@sha256:86b37d266ce85b485127adea68c9dc6d04d0ec9a64b0979844d5bbd8d66c53c5
Launch: llama.cpp-sycl-qwen3.8-27b-q4-k-m-128k-arc-pro-b65 ›
Recipe file: registry/recipes/intel/intel-arc-pro-b65-32gb/qwen3.8-27b.llama.cpp.128k.json ›
Model released: Aug 5, 2026
Tested: owner, Intel Arc Pro B65 32 GB (ASRock Creator; owner: Ryzen 7 5700X, PCIe 4.0 x4)