Instructions to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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("philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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 philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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 "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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": "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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 "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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 philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX

Run Hermes

hermes

OpenClaw new

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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 "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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 "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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 philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-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 "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

philipjohnbasile commited on 15 days ago

Commit

72b2299

verified ·

1 Parent(s): bf31e01

Upload design/DESIGN.md with huggingface_hub

Browse files

Files changed (1) hide show

design/DESIGN.md +7 -6

design/DESIGN.md CHANGED Viewed

@@ -90,12 +90,13 @@ The elite training lives in the heal corpus + the facet-inclusive calibration (`
 `80_family_eval.py` scores each via the soul gates):
 ```
-  99GB  : ████████ (baseline, current)
-  64GB  : should hold ~baseline   (~46 experts, 3-bit, 96GB Macs)
-  48GB  : should hold high        (~36 experts, 3-bit, 64GB Macs)
-  28GB  : the squeeze — watch which facets dip   (~26 experts, 2.5-bit, 36-48GB Macs)
-  14GB  : ⚗️ where does the soul start to break?  (~16 experts, 2-bit, 24GB Macs)
-   7GB  : ⚗️ the floor             (~8 experts, 2-bit, 16GB laptops)
 ```
 Per size: facet-calib → saliency → prune harder → quantize → heal (the soul corpus) → scorecard (% elite per

 `80_family_eval.py` scores each via the soul gates):
 ```
+ ~106GB : ████████  77 experts · 3-bit  (baseline, this model)   → 128 GB Mac
+   67GB : ██████    46 experts · 3-bit                           → 96 GB Mac
+   55GB : █████     36 experts · 3-bit                           → 64 GB Mac
+   36GB : ███       26 experts · 2.5-bit                         → 48 GB Mac
+   20GB : ██        16 experts · 2-bit  ⚗️                        → 32 GB Mac
+   14GB : █          8 experts · 2-bit  ⚗️ (floor; ~10.4GB base)  → 24 GB Mac
+  (sizes MEASURED: ~10.4GB fixed base + experts × ~1.24GB × bits/3; <~13GB impossible)
 ```
 Per size: facet-calib → saliency → prune harder → quantize → heal (the soul corpus) → scorecard (% elite per