Swift-1.5-Qwen3.8-27B

· llama.cpp · 256K context · Arc Pro B70 · 32 GB

UkisAI's post-training of Qwen3.8-27B for long-horizon agentic and coding work: it spends 58.5% fewer thinking tokens than Swift 1.0 while scoring slightly higher. The GSQ-RCO quants reuse ISTA-DASLab's published per-tensor allocation, refined with a Swift importance matrix, so IQ3_S lands at a KLD of 0.0417.

26 tok/sdecode

661 tok/sprefill

256Kcontext window

Tested on this cardOct 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 ukisai/Swift-1.5-Qwen3.8-27B-GGUF Swift-1.5-Qwen3.8-27B-Q4_K_M.gguf \
  --revision 14bfe4b42be4a925d98816db830155f476c605e7 \
  --local-dir ~/models/Swift-1.5-Qwen3.8-27B-GGUF-14bfe4b4

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/Swift-1.5-Qwen3.8-27B-GGUF-14bfe4b4:/models:ro \
  ghcr.io/ggml-org/llama.cpp@sha256:86b37d266ce85b485127adea68c9dc6d04d0ec9a64b0979844d5bbd8d66c53c5 \
  -m /models/Swift-1.5-Qwen3.8-27B-Q4_K_M.gguf \
  --alias Swift-1.5-Qwen3.8-27B-GGUF \
  --host 0.0.0.0 \
  --port 8080 \
  --ctx-size 262144 \
  --n-gpu-layers 999 \
  --parallel 1 \
  --flash-attn on \
  --batch-size 2048 \
  --ubatch-size 2048 \
  --cache-type-k q8_0 \
  --cache-type-v q8_0 \
  --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 B70 32 GB (owner: omarchy box, EPYC 7443P, card 0000:48:00.0) on Oct 16, 2026.

Details

Weights: ukisai/Swift-1.5-Qwen3.8-27B-GGUF @ 14bfe4b42b ›
Image: ghcr.io/ggml-org/llama.cpp@sha256:86b37d266ce85b485127adea68c9dc6d04d0ec9a64b0979844d5bbd8d66c53c5
Launch: llama.cpp-sycl-swift-1.5-qwen3.8-27b-q4-k-m-256k-kvq80-arc-pro-b70 ›
Recipe file: registry/recipes/intel/intel-arc-pro-b70-32gb/swift-1.5-qwen3.8-27b.llama.cpp.256k.json ›
Model released: Sep 16, 2026
Tested: owner, Intel Arc Pro B70 32 GB (owner: omarchy box, EPYC 7443P, card 0000:48:00.0)