Instructions to use mlx-community/GLM-5.1-DQ4plus-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/GLM-5.1-DQ4plus-q8 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("mlx-community/GLM-5.1-DQ4plus-q8")

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)

Transformers

How to use mlx-community/GLM-5.1-DQ4plus-q8 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mlx-community/GLM-5.1-DQ4plus-q8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/GLM-5.1-DQ4plus-q8")
model = AutoModelForCausalLM.from_pretrained("mlx-community/GLM-5.1-DQ4plus-q8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use mlx-community/GLM-5.1-DQ4plus-q8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/GLM-5.1-DQ4plus-q8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/GLM-5.1-DQ4plus-q8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlx-community/GLM-5.1-DQ4plus-q8

SGLang

How to use mlx-community/GLM-5.1-DQ4plus-q8 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mlx-community/GLM-5.1-DQ4plus-q8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/GLM-5.1-DQ4plus-q8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mlx-community/GLM-5.1-DQ4plus-q8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/GLM-5.1-DQ4plus-q8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use mlx-community/GLM-5.1-DQ4plus-q8 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-5.1-DQ4plus-q8"

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": "mlx-community/GLM-5.1-DQ4plus-q8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/GLM-5.1-DQ4plus-q8 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-5.1-DQ4plus-q8"

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-5.1-DQ4plus-q8

Run Hermes

hermes

MLX LM

How to use mlx-community/GLM-5.1-DQ4plus-q8 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/GLM-5.1-DQ4plus-q8"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/GLM-5.1-DQ4plus-q8"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/GLM-5.1-DQ4plus-q8",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use mlx-community/GLM-5.1-DQ4plus-q8 with Docker Model Runner:
```
docker model run hf.co/mlx-community/GLM-5.1-DQ4plus-q8
```

How does this style of quant stack up to the existing MXFP4 quant?

by harfum8 - opened 3 days ago

Discussion

harfum8

3 days ago

Do you have benchmark data to compare?

usermma

MLX Community org 3 days ago

no, its complex to generate one, if you know how to, or have time doing it, do it

harfum8

3 days ago

Seems like a lot of work to generate all these quants and have no data to back up the thesis. Thanks for contributing them though

usermma

MLX Community org 3 days ago

This comment has been hidden (marked as Low Quality)

usermma

MLX Community org 3 days ago

but its always known that the higher quant is better -

8-bit quant is better but slower in benchmarks than any lower than 8-bit quant:
which they are:
6-bit, 5-bit, 4-bit, 3-bit, 2-bit, or any lower

6-bit quant is better but slower in benchmarks than any lower than 6-bit quant
which they are:
5-bit, 4-bit, 3-bit, 2-bit, or any lower

5-bit quant is better but slower in benchmarks than any lower than 5-bit quant
which they are:
4-bit, 3-bit, 2-bit, or any lower

4-bit quant is better but slower in benchmarks than any lower than 4-bit quant
which they are:
3-bit, 2-bit, or any lower

3-bit quant is better but slower in benchmarks than any lower than 3-bit quant
which they are:
2-bit, or any lower

2-bit quant is better but slower in benchmarks than any lower than itself-bit quant
which they are:
any lower

harfum8

3 days ago

I agree, I want q8 for the "thinking" layers if they'll fit on my 512G M3U. Just would love to see benchmark data. What is your favorite model for 512 M3U right now?

usermma

MLX Community org 3 days ago

good answer!

FULL-ANSWER:

my favorite model for 512 M3U it would be:

Nex-N2-Pro

their benchmark compared to other models, -- is too fire!!

but its still in its road into i make a version of it into MLX

but it would highly take alot of time than you -- beacuse you have 512GB

i can show you the way how to do it and how to publish it in huggingface for other people......

Good thing that i made is i have made the mlx version of Nex-N2-Mini

you can on that machine run it full without any data-lose...

good thing that i already made is

making a MLX version of Nex-N2-mini

usermma/Nex-N2-mini-mlx-fp16

this is fp16 which means 16-bits without any quantization...

enjoy it.

usermma

MLX Community org 3 days ago

Benchmark	Nex-N2-mini	Nex-N2-Pro	GPT-5.5	Opus 4.7	Kimi-K2.6	GLM-5.1	MiniMax M3	DeepSeek-V4-Pro
Agent
BrowseComp	74.1	83.7	84.4	79.8	83.2	79.3	83.5	83.4
GDPval	1402	1585	1769	1753	1481	1535	-	1554
Toolathlon	33.3	51.9	55.6	52.8	50.0	40.7	-	51.8
WildClawBench	47.7	53.5	58.2	62.2	-	48.2	-	43.7
WideSearch	62.0	75.6	-	-	80.8	-	-	-
TAU3	65.9	71.1	-	-	-	70.6	-	-
Coding & SWE
SWE-Bench Pro	50.2	58.8	58.6	64.3	58.6	58.4	59.0	55.4
Terminal-Bench 2.1	60.7	75.3	83.4	69.7	-	58.7	66.0	72.0
DeepSWE	8.0	33.6	70	54	24	18	-	8
SWE-Bench Verified	74.4	80.8	82.9	87.6	80.2	-	80.5	80.6
SWE Atlas QnA	31.5	37.9	45.4	45.2	-	-	37.9	-
SWE Atlas RF	30.0	32.9	44.8	48.6	-	-	-	-
SWE Atlas TW	23.3	40.0	42.6	38.2	-	-	30.8	-
General & Reasoning
GPQA Diamond	82.6	90.7	93.6	94.2	90.5	86.2	-	90.1
IFEval	89.1	94.0	-	-	94.5	94.5	-	91.9
Apex	9.4	36.5	-	-	24.0	11.5	-	38.3

usermma

MLX Community org 3 days ago

i did not made it, i just copy and paste it from
https://huggingface.co/nex-agi/Nex-N2-Pro

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment