Instructions to use spicyneuron/GLM-5.2-MLX-4.5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spicyneuron/GLM-5.2-MLX-4.5bit 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("spicyneuron/GLM-5.2-MLX-4.5bit")

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 spicyneuron/GLM-5.2-MLX-4.5bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "spicyneuron/GLM-5.2-MLX-4.5bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "spicyneuron/GLM-5.2-MLX-4.5bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use spicyneuron/GLM-5.2-MLX-4.5bit 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 "spicyneuron/GLM-5.2-MLX-4.5bit"

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 spicyneuron/GLM-5.2-MLX-4.5bit

Run Hermes

hermes

MLX LM

How to use spicyneuron/GLM-5.2-MLX-4.5bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "spicyneuron/GLM-5.2-MLX-4.5bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "spicyneuron/GLM-5.2-MLX-4.5bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "spicyneuron/GLM-5.2-MLX-4.5bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

GLM-5.2-MLX-4.5bit / README.md

spicyneuron

Update README.md

db00e13 verified about 11 hours ago

preview code

Raw

History Blame Contribute Delete

1.49 kB

	---
	language:
	- en
	- zh
	library_name: mlx
	license: mit
	pipeline_tag: text-generation
	tags:
	- mlx
	base_model: zai-org/GLM-5.2
	---

	[zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) optimized for running on a Mac Studio M3 512.

	- A mixed-precision quant that balances speed, memory, and accuracy.
	- 4-bit baseline with important layers at higher precision.
	- Fits into ~420 GB memory, leaving enough room for a smaller utility model.


	# Usage

	NOTE: Run with https://github.com/ml-explore/mlx-lm/pull/1410 until the PR is merged.

	```sh
	# Start server at http://localhost:8080/v1/chat/completions
	uvx --from mlx-lm mlx_lm.server \
	--host 127.0.0.1 \
	--port 8080 \
	--model spicyneuron/GLM-5.2-MLX-4.5bit
	```

	# Benchmarks

	metric \| this model
	--- \| ---
	bpw \| 4.535
	base memory \| 392.454
	peak memory (1024/512) \| 422.787
	prompt tok/s (1024) \| 194.114 ± 0.079
	gen tok/s (512) \| 17.781 ± 0.028
	kl mean\* \| 0.049 ± 0.002
	kl p95 \| 0.113 ± 0.002
	perplexity \| 4.642 ± 0.036
	arc_challenge \| 0.690 ± 0.021
	hellaswag \| 0.780 ± 0.019

	\* KL calculated against the largest quant I could run locally (~5.3 bit). Real KL is against FP will be higher.

	# Methodology

	Quantized with a [mlx-lm fork](https://github.com/spicyneuron/mlx-lm/tree/override).
	MLX quantization options differ than llama.cpp, but the principles are the same:

	- Sensitive layers like MoE routing, attention, and output embeddings get higher precision
	- More tolerant layers like MoE experts get lower precision