Uncensored GLM 4.6V Flash MLX
Collection
3 items • Updated
How to use TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8 with MLX:
# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm
from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config
# Load the model
model, processor = load("TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8")
config = load_config("TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8")
# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."
# Apply chat template
formatted_prompt = apply_chat_template(
processor, config, prompt, num_images=1
)
# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)How to use TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8 with Pi:
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8"
# 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": "TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8"
}
]
}
}
}# Start Pi in your project directory: pi
How to use TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8 with Hermes Agent:
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8"
# 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 TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8
hermes
| Metric | This model | Original model (zai-org/GLM-4.6V-Flash) |
|---|---|---|
| KL divergence | 0.0000 | 0 (by definition) |
| Refusals | 63/100 | 100/100 |
| Parameter | Value |
|---|---|
| direction_index | 22.89 |
| attn.o_proj.max_weight | 1.45 |
| attn.o_proj.max_weight_position | 28.07 |
| attn.o_proj.min_weight | 1.40 |
| attn.o_proj.min_weight_distance | 13.38 |
| mlp.down_proj.max_weight | 1.19 |
| mlp.down_proj.max_weight_position | 24.88 |
| mlp.down_proj.min_weight | 0.82 |
| mlp.down_proj.min_weight_distance | 10.68 |
This model was converted to MLX format from AiAsistent/GLM-4.6V-Flash-heretic using mlx-vlm version 0.3.12.
8-bit
Base model
AiAsistent/GLM-4.6V-Flash-heretic