Instructions to use orcarouter/GLM-5.3-Flash-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use orcarouter/GLM-5.3-Flash-MLX with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("orcarouter/GLM-5.3-Flash-MLX")
config = load_config("orcarouter/GLM-5.3-Flash-MLX")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use orcarouter/GLM-5.3-Flash-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "orcarouter/GLM-5.3-Flash-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "orcarouter/GLM-5.3-Flash-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use orcarouter/GLM-5.3-Flash-MLX with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "orcarouter/GLM-5.3-Flash-MLX"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default orcarouter/GLM-5.3-Flash-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use orcarouter/GLM-5.3-Flash-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "orcarouter/GLM-5.3-Flash-MLX"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "orcarouter/GLM-5.3-Flash-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

hugging-yiii commited on 2 days ago

Commit

b689783

verified ·

1 Parent(s): 52fc8dc

Add 2bit-lite MLX quantization (1/9)

Browse files

Files changed (3) hide show

2bit-lite/model.safetensors.index.json +1 -1
2bit-lite/preprocessor_config.json +29 -0
2bit-lite/video_preprocessor_config.json +36 -0

2bit-lite/model.safetensors.index.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9f2bf562ba0691469229d78d843ac66c6e261991d417a6e1f1d534efcf351c
 size 11529499

 version https://git-lfs.github.com/spec/v1
+oid sha256:d27789250345c2d74c5a9ee371b453db491375ae9b5a05ecad1ae5f09cc73569
 size 11529499

2bit-lite/preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "do_rescale": true,
+  "patch_expand_factor": 1,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "temporal_patch_size": 2,
+  "patch_size": 14,
+  "min_image_tokens": 16,
+  "max_image_tokens": 8000,
+  "image_processor_type": "Glm5NextImageProcessor",
+  "do_convert_rgb": true,
+  "do_resize": true,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "do_normalize": true,
+  "size": {
+    "longest_edge": 1
+  },
+  "processor_class": "Glm5NextProcessor"
+}

2bit-lite/video_preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,36 @@

+{
+  "do_rescale": true,
+  "video_processor_type": "Glm5NextVideoProcessor",
+  "patch_expand_factor": 1,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "temporal_patch_size": 2,
+  "patch_size": 14,
+  "min_image_tokens": 16,
+  "max_image_tokens": 240000,
+  "fps": 2,
+  "do_convert_rgb": true,
+  "do_resize": true,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "do_normalize": true,
+  "do_sample_frames": true,
+  "num_frames": 16,
+  "return_metadata": false,
+  "max_image_size": {
+    "longest_edge": 47040000
+  },
+  "max_frames": 2048,
+  "size": {
+    "longest_edge": 1
+  }
+}