Instructions to use pipenetwork/GLM-5.2-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/GLM-5.2-MLX-8bit with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("pipenetwork/GLM-5.2-MLX-8bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use pipenetwork/GLM-5.2-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/GLM-5.2-MLX-8bit"

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": "pipenetwork/GLM-5.2-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use pipenetwork/GLM-5.2-MLX-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pipenetwork/GLM-5.2-MLX-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pipenetwork/GLM-5.2-MLX-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pipenetwork/GLM-5.2-MLX-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use pipenetwork/GLM-5.2-MLX-8bit 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 "pipenetwork/GLM-5.2-MLX-8bit"

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 pipenetwork/GLM-5.2-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pipenetwork/GLM-5.2-MLX-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/GLM-5.2-MLX-8bit"

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 "pipenetwork/GLM-5.2-MLX-8bit" \
  --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-5.2-MLX-8bit

Runtime — updated 2026-08-28: load with `--trust-remote-code`

This repository now bundles glm_moe_dsa.py (declared via model_file in config.json), a fixed runtime for this architecture, and needs it:

mlx_lm.generate --model pipenetwork/GLM-5.2-MLX-8bit --trust-remote-code --prompt "..." --max-tokens 300

mlx-lm's own glm_moe_dsa builds a lightning indexer on all 78 layers, but GLM-5.2 ships indexer weights on 21 (indexer_types: the other 57 "shared" layers reuse the previous full layer's top-k selection). mlx_lm.load loads leniently and left those 57 indexers at random initialisation. Prompts up to 2048 tokens were unaffected (the indexer is bypassed below index_topk); beyond that, 57 of 78 layers attended to keys chosen by random projections. The bundled runtime implements the schedule as the reference does (plus fp32 indexer scores and router logits and the indexer LayerNorm epsilon); tiny-config parity against transformers 5.16 is 4e-7 with the sparse path live, and a strict load of this checkpoint reports zero missing and zero unexpected tensors. Details, tests and the GLM-5.3 builds made with it: github.com/PipeNetwork/glm53-mlx. The weights are unchanged.

MLX (Apple Silicon) conversion of zai-org/GLM-5.2 — a glm_moe_dsa MoE (256 experts, DeepSeek-V3.2-style sparse attention) — quantized to 8-bit.

Quantizations

Part of the GLM-5.2 MLX collection.

Variant	Notes
8-bit (this repo)	8-bit · ~800GB · needs ~1TB RAM · integrity-checked
6-bit	6-bit · ~625GB · needs ~768GB RAM · integrity-checked
5-bit	5-bit · ~530GB · needs ~640GB RAM · integrity-checked
4-bit	4-bit · ~430GB · tight on 512GB · smoke-tested
mixed	mixed · experts@3-bit / non-expert@6-bit · ~360GB · 512GB-fit · smoke-tested

Use with mlx-lm

pip install mlx-lm
python -m mlx_lm generate --model pipenetwork/GLM-5.2-MLX-8bit --prompt "Hello" -m 256

Validation

File-integrity checked (index/shards/config/tokenizer); not run-tested (exceeds the 512GB conversion host's RAM).

License

MIT (inherited from base). Quantization config (excerpt): {"group_size": 64, "bits": 8, "mode": "affine"}.

Downloads last month: 140

Safetensors

Model size

743B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

8-bit

Model tree for pipenetwork/GLM-5.2-MLX-8bit

Base model

zai-org/GLM-5.2

Quantized

(149)

this model

Collection including pipenetwork/GLM-5.2-MLX-8bit

GLM-5.2 MLX

Collection

First MLX builds of zai-org/GLM-5.2 (glm_moe_dsa MoE): 4/5/6/8-bit + a 512GB-friendly mixed. • 6 items • Updated Jun 26 • 1

GLM-5.2-MLX-8bit

Runtime — updated 2026-08-28: load with --trust-remote-code

Quantizations

Use with mlx-lm

Validation

License

Model tree for pipenetwork/GLM-5.2-MLX-8bit

Collection including pipenetwork/GLM-5.2-MLX-8bit

Runtime — updated 2026-08-28: load with `--trust-remote-code`