Instructions to use spicyneuron/GLM-5.1-MLX-4.5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spicyneuron/GLM-5.1-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-5.1-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-5.1-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-5.1-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-5.1-MLX-4.5bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use spicyneuron/GLM-5.1-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-5.1-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-5.1-MLX-4.5bit

Run Hermes

hermes

MLX LM

How to use spicyneuron/GLM-5.1-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-5.1-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-5.1-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-5.1-MLX-4.5bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

GLM 5.1 optimized to run on a Mac Studio M3 512. This is the quality-first version. Alternatives: speed-first, balanced

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 plenty of room to run a smaller parallel model (ex: Qwen 3.6 35B).

Usage

# 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-4.5bit

Benchmarks

metric	baa-ai/GLM-5.1-RAM-270GB-MLX	2.9 bit	3.6 bit	4.5 bit (this model)
bpw	3.110	2.906	3.645	4.538
base memory	269.303	251.702	315.648	392.992
peak memory (1024/512)	291.257	272.358	341.020	424.067
prompt tok/s (1024)	194.958 ± 0.075	194.216 ± 0.167	190.508 ± 0.880	193.563 ± 0.094
gen tok/s (512)	21.381 ± 0.050	19.527 ± 0.035	17.873 ± 0.156	17.259 ± 0.032
kl mean*	0.686 ± 0.054	0.268 ± 0.009	0.117 ± 0.004	0.048 ± 0.002
kl p95*	1.478 ± 0.054	0.537 ± 0.009	0.236 ± 0.004	0.097 ± 0.002
perplexity	4.780 ± 0.020	4.118 ± 0.016	3.945 ± 0.016	3.920 ± 0.016
piqa	0.776 ± 0.010	0.794 ± 0.009	0.820 ± 0.017	0.814 ± 0.017

* GLM 5.1 KL divergence calculated against the largest quant I could run locally (~495 GB), so real KL is higher.

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

mlx_lm.kld is approximate, based on top_k not full logits. Here's the code.

Methodology

Quantized with a mlx-lm fork, 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

Downloads last month: 774

Safetensors

Model size

744B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

4-bit

Model tree for spicyneuron/GLM-5.1-MLX-4.5bit

Base model

zai-org/GLM-5.1

Quantized

(40)

this model