Instructions to use spicyneuron/GLM-5.1-MLX-3.6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spicyneuron/GLM-5.1-MLX-3.6bit 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-3.6bit")

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-3.6bit 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-3.6bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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-3.6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use spicyneuron/GLM-5.1-MLX-3.6bit 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-3.6bit"

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-3.6bit"
# 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-3.6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use spicyneuron/GLM-5.1-MLX-3.6bit 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-3.6bit"

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-3.6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use spicyneuron/GLM-5.1-MLX-3.6bit with OpenClaw:

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-3.6bit"

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 "spicyneuron/GLM-5.1-MLX-3.6bit" \
  --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"

spicyneuron commited on Jun 2

Commit

7f27410

verified ·

1 Parent(s): 027348d

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -8

README.md CHANGED Viewed

@@ -38,11 +38,13 @@ uvx --from mlx-lm mlx_lm.server \
 | 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 |
 Tested on a Mac Studio M3 Ultra with:
 ```
@@ -52,10 +54,7 @@ mlx_lm.benchmark --prompt-tokens 1024 --generation-tokens 512 --num-trials 5
 mlx_lm.evaluate --tasks piqa --seed 123 --num-shots 0 --limit 500
 ```
-Note:
-- `mlx_lm.kld` is approximate, based on `top_k` not full logits. Here's the [code](https://github.com/ml-explore/mlx-lm/pull/1146).
-- GLM 5.1 KL divergence calculated against the largest quant I could run locally (~495 GB), so real KL is higher.
 # Methodology
@@ -65,5 +64,4 @@ 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

 | 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.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](https://github.com/ml-explore/mlx-lm/pull/1146).
 # Methodology
 same:
 - Sensitive layers like MoE routing, attention, and output embeddings get higher precision
+- More tolerant layers like MoE experts get lower precision