Instructions to use mlx-community/GLM-5.3-Flash-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/GLM-5.3-Flash-4bit 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("mlx-community/GLM-5.3-Flash-4bit")
config = load_config("mlx-community/GLM-5.3-Flash-4bit")

# 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 mlx-community/GLM-5.3-Flash-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/GLM-5.3-Flash-4bit"

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": "mlx-community/GLM-5.3-Flash-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use mlx-community/GLM-5.3-Flash-4bit 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 "mlx-community/GLM-5.3-Flash-4bit"

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 mlx-community/GLM-5.3-Flash-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/GLM-5.3-Flash-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/GLM-5.3-Flash-4bit"

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 "mlx-community/GLM-5.3-Flash-4bit" \
  --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"

mlx-community/GLM-5.3-Flash-4bit

zai-org/GLM-5.3-Flash in MLX affine format, mixed 4/5/6-bit, group size 64.

The weights are the 4-bit variant of orcarouter/GLM-5.3-Flash-MLX (revision c80f6810b1a95b5be9042761becc6aa78d189782, the 4-bit/ build, which is also the repo root there). The quantisation is orcarouter's. The 62 safetensors shards are byte-identical to that build (sha256 checked).

Change from the source: config.json now lists the per-module widths of the MTP layer (layer 45) in quantization and quantization_config. The source config named them for layers 3-44 only. The tensors are not changed.

Size: 62 shards, 203,992,076,296 bytes (190 GiB). It needs a Mac with 256 GB of memory or more.

Widths

Read from each tensor's shapes (bits = 32 * weight_columns / (group_size * scales_columns)), group size 64 throughout.

Modules	Layers	Bits
Routed experts `gate_proj`, `up_proj`	3-45	4
Routed experts `down_proj`	3-45	5
Shared expert `gate_proj`, `up_proj`, `down_proj`	3-45	6
Dense MLP `gate_proj`, `up_proj`	0-2	4
Dense MLP `down_proj`	0-2	5
Sparse attention `q_a_proj`, `q_b_proj`, `kv_a_proj_with_mqa`, `o_proj`	3, 7, 11, ..., 43, 45 (12 layers)	4
Linear attention layers, `kv_b_proj`, indexer, router, mHC, norms, `embed_tokens`, `lm_head`, MTP `eh_proj`, vision tower	all	bf16

Layer 45 is the MTP (next-token prediction) layer.

Usage

mlx-lm does not support the glm5_next architecture. mlx-vlm has a glm5_next model; see the orcarouter model card for its use.

License

MIT, the same as the base model.

Downloads last month: 364

Safetensors

Model size

348B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

4-bit

Model tree for mlx-community/GLM-5.3-Flash-4bit

Base model

zai-org/GLM-5.3-Flash

Quantized

(123)

this model