GLM-5.3-Flash

MLX 4-bit (g64), native MTP · omlx · 1024K context · Apple M5 Ultra · 256 GB

Z.ai's GLM-5.3-Flash, a large mixture-of-experts model for multi-GPU machines.

41 tok/sdecode

560 tok/sprefill

1024Kcontext window

Earlier checkSep 25, 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 Install the engine

python3 -m pip install 'omlx @ https://github.com/jundot/omlx/releases/download/v0.7.0.dev4/omlx-0.7.0.dev4-cp313-cp313-macosx_15_0_universal2.whl'

2 Download the weights

hf download Vontra/GLM-5.3-Flash-MLX-4bit-MTP \
  --revision 76add2a341a1cd90ad0e86bb69839ea9c35827c6 \
  --local-dir models/GLM-5.3-Flash-MLX-4bit-MTP

3 Write the launcher

mkdir -p omlx-home
cat > omlx-home/model_settings.json <<'EOF'
{
  "version": 1,
  "models": {
    "GLM-5.3-Flash-MLX-4bit-MTP": {
      "mtp_enabled": true
    }
  }
}
EOF

4 Start the server

HF_HUB_OFFLINE=1 \
  omlx \
  serve \
  --model-dir models \
  --base-path omlx-home \
  --host 127.0.0.1 \
  --port 8000

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 the older check (loads and chats); a full six-check run is pending.

Details

Weights: Vontra/GLM-5.3-Flash-MLX-4bit-MTP @ 76add2a341 ›
Image: none: a program on the host
Launch: omlx-glm-5.3-flash-4bit-mtp-1024k ›
Recipe file: registry/recipes/apple/apple-m5-ultra-256gb/glm-5.3-flash.omlx.1024k.json ›
Model released: Aug 25, 2026
Tested: earlier acceptance