Instructions to use spicyneuron/GLM-5.1-MLX-2.9bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spicyneuron/GLM-5.1-MLX-2.9bit 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-5.1-MLX-2.9bit")

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
LM Studio

Pi new

How to use spicyneuron/GLM-5.1-MLX-2.9bit 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-5.1-MLX-2.9bit"

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-5.1-MLX-2.9bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use spicyneuron/GLM-5.1-MLX-2.9bit 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-5.1-MLX-2.9bit"

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-5.1-MLX-2.9bit

Run Hermes

hermes

MLX LM

How to use spicyneuron/GLM-5.1-MLX-2.9bit 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-5.1-MLX-2.9bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "spicyneuron/GLM-5.1-MLX-2.9bit"
# 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-5.1-MLX-2.9bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

GLM-5.1-MLX-2.9bit / README.md

spicyneuron

Update README.md

3ced8e0 verified 24 days ago

preview code

raw

history blame contribute delete

2.36 kB

	---
	language:
	- en
	- zh
	library_name: mlx
	license: mit
	pipeline_tag: text-generation
	base_model: zai-org/GLM-5.1
	tags:
	- mlx
	---

	[GLM 5.1](https://huggingface.co/zai-org/GLM-5.1) optimized to run _comfortably_
	on a Mac Studio M3 512. This is the smaller, compact version. Quality-first
	version [here](https://huggingface.co/spicyneuron/GLM-5.1-MLX-3.6bit).

	- A mixed-precision quant that balances speed, memory, and accuracy.
	- 3-bit baseline with important layers at 4, 8 and BF16.
	- Fits into ~280 GB memory, leaving plenty of room to run parallel models (ex: Minimax M2.7, Qwen 3.6 35B).

	# Usage

	```sh
	# Start server at http://localhost:8080/chat/completions
	uvx --from mlx-lm mlx_lm.server \
	--host 127.0.0.1 \
	--port 8080 \
	--model spicyneuron/GLM-5.1-MLX-2.9bit
	```

	# Benchmarks

	metric \| baa-ai/GLM-5.1-RAM-270GB-MLX \| 2.9 bit (this model) \| 3.6 bit
	--- \| --- \| --- \| ---
	bpw \| 3.110 \| 2.906 \| 3.645
	base memory \| 269.303 \| 251.702 \| 315.648
	peak memory (1024/512) \| 291.257 \| 272.358 \| 341.020
	prompt tok/s (1024) \| 194.958 ± 0.075 \| 194.216 ± 0.167 \| 190.508 ± 0.880
	gen tok/s (512) \| 21.381 ± 0.050 \| 19.527 ± 0.035 \| 17.873 ± 0.156
	kl mean \| 0.686 ± 0.054 \| 0.268 ± 0.009 \| 0.117 ± 0.004
	kl p95 \| 1.478 ± 0.054 \| 0.537 ± 0.009 \| 0.236 ± 0.004
	perplexity \| 4.780 ± 0.020 \| 4.118 ± 0.016 \| 3.945 ± 0.016
	piqa \| 0.776 ± 0.010 \| 0.794 ± 0.009 \| 0.820 ± 0.017

	Tested on a Mac Studio M3 Ultra with:

	```
	mlx_lm.kld --baseline-model path/to/mlx-full-precision
	mlx_lm.perplexity --sequence-length 2048 --seed 123
	mlx_lm.benchmark --prompt-tokens 1024 --generation-tokens 512 --num-trials 5
	mlx_lm.evaluate --tasks piqa --seed 123 --num-shots 0 --limit 500
	```

	Note:

	- `mlx_lm.kld` is approximate, based on `top_k` not full logits. Here's the [code](https://github.com/ml-explore/mlx-lm/pull/1146).
	- GLM 5.1 KL divergence calculated against the largest quant I could run locally (~495 GB), so real KL is higher.

	# Methodology

	Quantized with a [mlx-lm fork](https://github.com/ml-explore/mlx-lm/pull/922),
	drawing inspiration from Unsloth/AesSedai/ubergarm style mixed-precision GGUFs.
	MLX quantization options differ from 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