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

Libraries

How to use JANGQ-AI/GLM-5.3-Flash-JANG 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("JANGQ-AI/GLM-5.3-Flash-JANG")
config = load_config("JANGQ-AI/GLM-5.3-Flash-JANG")

# 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 JANGQ-AI/GLM-5.3-Flash-JANG with Pi:

Start the MLX server

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

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": "JANGQ-AI/GLM-5.3-Flash-JANG"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use JANGQ-AI/GLM-5.3-Flash-JANG 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 "JANGQ-AI/GLM-5.3-Flash-JANG"

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 JANGQ-AI/GLM-5.3-Flash-JANG

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JANGQ-AI/GLM-5.3-Flash-JANG with OpenClaw:

Start the MLX server

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

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 "JANGQ-AI/GLM-5.3-Flash-JANG" \
  --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"

jangq commited on 9 days ago

Commit

8425574

verified ·

1 Parent(s): 8e9a435

comparison chart

Browse files

Files changed (1) hide show

README.md +15 -1

README.md CHANGED Viewed

@@ -50,7 +50,21 @@ Sibling bundle: [GLM-5.3-Flash-JANG-MTP](https://huggingface.co/JANGQ-AI/GLM-5.3
 | JANG-MTP | 95.47 GiB | 0.0977 | 0.552 | 1.57 / 2.63 / 5.74 | 78.1% | 94.4% | 96.7% |
 | **JANG (AR)** | **95.48 GiB** | **0.0885** | **0.529** | **1.50 / 2.56 / 5.64** | **78.7%** | **94.6%** | **96.9%** |
-For calibration: our dots3-note release (280B at 94.6 GiB) ships at 79.2% top-1 — this model carries ~305B of routed experts with no fp16 embedding table to absorb signal, so these numbers are the honest physics of ~2.2 effective bits at this size. Comparison rows for other public quants are being measured on the identical protocol and will be added.
 ## Calibration data

 | JANG-MTP | 95.47 GiB | 0.0977 | 0.552 | 1.57 / 2.63 / 5.74 | 78.1% | 94.4% | 96.7% |
 | **JANG (AR)** | **95.48 GiB** | **0.0885** | **0.529** | **1.50 / 2.56 / 5.64** | **78.7%** | **94.6%** | **96.9%** |
+For calibration: our dots3-note release (280B at 94.6 GiB) ships at 79.2% top-1 — this model carries ~305B of routed experts with no fp16 embedding table to absorb signal, so these numbers are the honest physics of ~2.2 effective bits at this size.
+## How it compares (same protocol, same reference, same positions)
+| Quant (95 GiB class) | Size | median KL ↓ | mean KL ↓ | top-1 ↑ | top-5 ↑ | top-10 ↑ |
+|---|---|---|---|---|---|---|
+| **GLM-5.3-Flash-JANG (AR)** | 95.35 GiB | **0.0885** | **0.52** | **78.7%** | **94.6%** | **96.8%** |
+| **GLM-5.3-Flash-JANG-MTP** | 95.47 GiB | 0.0977 | 0.55 | 78.1% | 94.4% | 96.7% |
+| orcarouter GLM-5.3-Flash-MLX `2bit-lite` | 95.4 GiB | 0.2122 | 0.83 | 71.4% | 90.8% | 94.3% |
+All rows: 15,850 teacher-forced positions vs the official FP8 release
+(top-128 renormalized KL). The orcarouter bundle was evaluated by loading its
+quantized weights natively — its exact shipped fidelity, no requantization.
+antirez's `GLM-5.3-Flash-Q2.gguf` (89.9 GiB) could not be measured: no public
+llama.cpp build (mainline or the open support PR) currently loads those files.
 ## Calibration data