Instructions to use Jundot/GLM-5.3-Flash-oQ4e-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jundot/GLM-5.3-Flash-oQ4e-mtp 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("Jundot/GLM-5.3-Flash-oQ4e-mtp")
config = load_config("Jundot/GLM-5.3-Flash-oQ4e-mtp")

# 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 Jundot/GLM-5.3-Flash-oQ4e-mtp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Jundot/GLM-5.3-Flash-oQ4e-mtp"

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": "Jundot/GLM-5.3-Flash-oQ4e-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use Jundot/GLM-5.3-Flash-oQ4e-mtp 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 "Jundot/GLM-5.3-Flash-oQ4e-mtp"

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 Jundot/GLM-5.3-Flash-oQ4e-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Jundot/GLM-5.3-Flash-oQ4e-mtp with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Jundot/GLM-5.3-Flash-oQ4e-mtp"

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 "Jundot/GLM-5.3-Flash-oQ4e-mtp" \
  --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"

GLM-5.3-Flash-oQ4e-mtp

This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385).

A mixed-precision MLX checkpoint of zai-org/GLM-5.3-Flash, a natively multimodal mixture-of-experts model with 320B total and 18B active parameters that combines sparse and linear attention with Manifold-Constrained Hyper-Connections (mHC). It includes the language model, the vision encoder and the multi-token prediction (MTP) head.

The effective average is 4.629 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

oQ4e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (128 samples x 512 tokens) and a weighted least-squares refit of its scale and bias.

Storage format	Logical weights	Share of total	Tensor storage	Effective bits/weight
Affine 4-bit, group 64	311.654B	96.991%	163.266 GiB	4.50
Affine 5-bit, group 64	0.933B	0.290%	0.598 GiB	5.50
Affine 6-bit, group 64	0.503B	0.157%	0.381 GiB	6.50
Affine 8-bit, group 64	7.539B	2.346%	7.460 GiB	8.50
BF16	0.607B	0.189%	1.131 GiB	16.00
FP32	0.086B	0.027%	0.322 GiB	32.00
Total	321.323B	100%	173.157 GiB	4.629

Storage Breakdown

Component	Logical weights	Storage
Language backbone	313.327B	180.522 GB / 168.124 GiB
Vision encoder	0.564B	1.127 GB / 1.050 GiB
MTP head	7.433B	4.277 GB / 3.983 GiB
Total	321.323B	185.926 GB / 173.157 GiB

License

MIT, following the source model. See LICENSE.

Downloads last month: 4,465

Safetensors

Model size

321B params

Tensor type

U32

F32

BF16

MLX

Hardware compatibility

4-bit

Model tree for Jundot/GLM-5.3-Flash-oQ4e-mtp

Base model

zai-org/GLM-5.3-Flash

Quantized

(192)

this model