Qwen3.6-35B-A3B

· llama.cpp · 256K context · RTX 5070 · 12 GB

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

39 tok/sdecode

876 tok/sprefill

256Kcontext window

Tested on this cardOct 8, 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-MTP-GGUF Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf \
  --revision 5bc3e238d916f48a861bac2f8a1990a0e9b7e98d \
  --local-dir ~/models/Qwen3.6-35B-A3B-MTP-GGUF-5bc3e238

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:8080 \
  --shm-size 16g \
  -e CUDA_DEVICE_ORDER=PCI_BUS_ID \
  -v ~/models/Qwen3.6-35B-A3B-MTP-GGUF-5bc3e238:/models:ro \
  --entrypoint /app/llama-server \
  ghcr.io/ggml-org/llama.cpp:server-cuda12-b11146@sha256:52192a23c7b258044463aebba78826cdff39a7393b713edc313324b343a7b836 \
  --model /models/Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf \
  --cache-type-k q8_0 \
  --cache-type-v q8_0 \
  --load-mode none \
  --host 0.0.0.0 \
  --port 8080 \
  --ctx-size 262144 \
  --flash-attn on \
  --parallel 1 \
  --jinja \
  --no-mmproj \
  --cache-ram 0 \
  --metrics \
  --spec-type draft-mtp \
  --spec-draft-n-max 3 \
  --temp 1.0 \
  --top-p 0.95 \
  --top-k 20 \
  --min-p 0.0

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 RTX 5070 on Oct 8, 2026.

Details

Weights: unsloth/Qwen3.6-35B-A3B-MTP-GGUF @ 5bc3e238d9 ›
Image: ghcr.io/ggml-org/llama.cpp:server-cuda12-b11146@sha256:52192a23c7b258044463aebba78826cdff39a7393b713edc313324b343a7b836
Launch: llama.cpp-qwen3.6-35b-a3b-mtp-ud-q4-k-xl-autofit-256k-rtx-5070-12gb ›
Recipe file: registry/recipes/nvidia/rtx-5070-12gb/qwen3.6-35b-a3b.llama.cpp.256k.json ›
Model released: Apr 15, 2026
Tested: owner, RTX 5070