Welp-35B-A3B

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

Quaedra's 13.2 GB GGUF of Qwen3.6-35B-A3B: the routed experts quantized block-wise with GPTQ error feedback in standard llama.cpp formats, so the full 262k context fits on a 16 GB card.

83 tok/sdecode

1,216 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 quaedra/Welp-35B-A3B-GGUF Welp-35B-A3B.gguf \
  --revision 3e4a3adbda8df07d2889978170d9955c2e59fb7a \
  --local-dir ~/models/Welp-35B-A3B-GGUF-3e4a3adb

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/Welp-35B-A3B-GGUF-3e4a3adb:/models:ro \
  ghcr.io/ggml-org/llama.cpp@sha256:86b37d266ce85b485127adea68c9dc6d04d0ec9a64b0979844d5bbd8d66c53c5 \
  -m /models/Welp-35B-A3B.gguf \
  --alias Welp-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: quaedra/Welp-35B-A3B-GGUF @ 3e4a3adbda ›
Image: ghcr.io/ggml-org/llama.cpp@sha256:86b37d266ce85b485127adea68c9dc6d04d0ec9a64b0979844d5bbd8d66c53c5
Launch: llama.cpp-sycl-welp-35b-a3b-gguf-256k-arc-pro-b70 ›
Recipe file: registry/recipes/intel/intel-arc-pro-b70-32gb/welp-35b-a3b.llama.cpp.256k.json ›
Model released: Oct 8, 2026
Tested: owner, Intel Arc Pro B70 32 GB (owner: omarchy box, EPYC 7443P, card 0000:48:00.0)