Instructions to use LibraxisAI/QwQ-32B-MLX-Q5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LibraxisAI/QwQ-32B-MLX-Q5 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("LibraxisAI/QwQ-32B-MLX-Q5")

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 LibraxisAI/QwQ-32B-MLX-Q5 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LibraxisAI/QwQ-32B-MLX-Q5"

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": "LibraxisAI/QwQ-32B-MLX-Q5"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use LibraxisAI/QwQ-32B-MLX-Q5 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "LibraxisAI/QwQ-32B-MLX-Q5"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "LibraxisAI/QwQ-32B-MLX-Q5"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "LibraxisAI/QwQ-32B-MLX-Q5",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use LibraxisAI/QwQ-32B-MLX-Q5 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 "LibraxisAI/QwQ-32B-MLX-Q5"

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 LibraxisAI/QwQ-32B-MLX-Q5

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LibraxisAI/QwQ-32B-MLX-Q5 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LibraxisAI/QwQ-32B-MLX-Q5"

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 "LibraxisAI/QwQ-32B-MLX-Q5" \
  --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"

mszymanska commited on May 11

Commit

d2f306f

verified ·

1 Parent(s): 56e07b6

docs: add Tested inference path section, reorganize model card

Browse files

Files changed (1) hide show

README.md +15 -10

README.md CHANGED Viewed

@@ -51,6 +51,20 @@ widget:
 This card only reports metadata present in the Hugging Face repository, existing card frontmatter, or public config files. Missing benchmark, dataset, or training-run details are left explicit rather than reconstructed.
 ## Usage
 ### CLI
@@ -96,7 +110,7 @@ print(response)
 ## Example output
-No public sample output is currently declared for this checkpoint. Run the usage example above against your own prompt or audio/image input to inspect behavior.
 ## Quantization notes
@@ -129,15 +143,6 @@ No public sample output is currently declared for this checkpoint. Run the usage
   note = {MLX checkpoint published by LibraxisAI}
 }
 ```
-## Inference tested on
-[`LibraxisAI/mlx-batch-server`](https://github.com/LibraxisAI/mlx-batch-server)
-## Related
-- Base model: [`Qwen/QwQ-32B`](https://huggingface.co/Qwen/QwQ-32B)
 ---
 𝚅𝚒𝚋𝚎𝚌𝚛𝚊𝚏𝚝𝚎𝚍. with AI Agents by VetCoders (c)2024-2026 LibraxisAI

 This card only reports metadata present in the Hugging Face repository, existing card frontmatter, or public config files. Missing benchmark, dataset, or training-run details are left explicit rather than reconstructed.
+## Tested inference path
+> **Inference for this checkpoint has been tested with [`LibraxisAI/mlx-batch-server`](https://github.com/LibraxisAI/mlx-batch-server).**\
+> This is the recommended tested path for operator-controlled local inference on Apple Silicon.
+| Aspect | Status |
+|---|---|
+| Tested runtime | `LibraxisAI/mlx-batch-server` |
+| Target hardware | Apple Silicon |
+| Inference mode | Local / self-hosted |
+| Hugging Face Hosted Inference | Disabled for this repository (`inference: false`) |
+This does not claim compatibility with every possible serving stack. It documents the path that has been exercised for this published checkpoint.
 ## Usage
 ### CLI
 ## Example output
+No public sample output is currently declared for this checkpoint.
 ## Quantization notes
   note = {MLX checkpoint published by LibraxisAI}
 }
 ```
 ---
 𝚅𝚒𝚋𝚎𝚌𝚛𝚊𝚏𝚝𝚎𝚍. with AI Agents by VetCoders (c)2024-2026 LibraxisAI