Instructions to use nightmedia/GLM-4.7-Flash-7e-qx85g-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nightmedia/GLM-4.7-Flash-7e-qx85g-mlx 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("nightmedia/GLM-4.7-Flash-7e-qx85g-mlx")

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 nightmedia/GLM-4.7-Flash-7e-qx85g-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nightmedia/GLM-4.7-Flash-7e-qx85g-mlx"

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": "nightmedia/GLM-4.7-Flash-7e-qx85g-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use nightmedia/GLM-4.7-Flash-7e-qx85g-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nightmedia/GLM-4.7-Flash-7e-qx85g-mlx"

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 "nightmedia/GLM-4.7-Flash-7e-qx85g-mlx" \
  --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"

MLX LM

How to use nightmedia/GLM-4.7-Flash-7e-qx85g-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nightmedia/GLM-4.7-Flash-7e-qx85g-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nightmedia/GLM-4.7-Flash-7e-qx85g-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nightmedia/GLM-4.7-Flash-7e-qx85g-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use nightmedia/GLM-4.7-Flash-7e-qx85g-mlx 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 "nightmedia/GLM-4.7-Flash-7e-qx85g-mlx"

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 nightmedia/GLM-4.7-Flash-7e-qx85g-mlx

Run Hermes

hermes

Hope this helps

by McG-221 - opened Jan 20

Discussion

McG-221

Jan 20

Have you already tried these? ✌️

nightmedia

Owner Jan 20

yes, of course, but that's beside the point. The model should be stable at all temps. All my qwens play nice in the entire range of temp/settings, and I make it a point to test for that stability. If a model can be "fixed" by changing temp, it's not a stable model.

McG-221

Jan 20

•

edited Jan 20

Absolutely! I'm glad to hear we're on the same page 💪

I mean, you may have noticed how much I like it to search for local optima... 🙄

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