Qwen3.6-35B-A3B

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

Qwen3.6's 35B mixture-of-experts model with 3B active parameters.

90 tok/sdecode

1,212 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 unsloth/Qwen3.6-35B-A3B-GGUF Qwen3.6-35B-A3B-UD-Q4_K_M.gguf \
  --revision a483e9e6cbd595906af30beda3187c2663a1118c \
  --local-dir ~/models/Qwen3.6-35B-A3B-GGUF-a483e9e6

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/Qwen3.6-35B-A3B-GGUF-a483e9e6:/models:ro \
  ghcr.io/ggml-org/llama.cpp@sha256:86b37d266ce85b485127adea68c9dc6d04d0ec9a64b0979844d5bbd8d66c53c5 \
  -m /models/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf \
  --alias Qwen3.6-35B-A3B-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 \
  --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: unsloth/Qwen3.6-35B-A3B-GGUF @ a483e9e6cb ›
Image: ghcr.io/ggml-org/llama.cpp@sha256:86b37d266ce85b485127adea68c9dc6d04d0ec9a64b0979844d5bbd8d66c53c5
Launch: llama.cpp-sycl-qwen3.6-35b-a3b-ud-q4-k-m-256k-arc-pro-b70 ›
Recipe file: registry/recipes/intel/intel-arc-pro-b70-32gb/qwen3.6-35b-a3b.llama.cpp.256k.json ›
Model released: Apr 15, 2026
Tested: owner, Intel Arc Pro B70 32 GB (owner: omarchy box, EPYC 7443P, card 0000:48:00.0)