Instructions to use inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF 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("inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF")

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 inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF"

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": "inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF 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 "inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF"

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 inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF"

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 "inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF" \
  --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"

Macaron-V1-Coding-Venti-Q4.8-INF

See Macaron-V1-Coding-Venti in action: demonstration videos

Tested with an M3 Ultra 512 GiB using Inferencer app

Text Inference: ~14.7 tokens/s @ 1000 tokens ~414.8 GiB

Q4.8-INF uses the data-agnostic INF method tuned to yield maximum general accuracy within a 512 GiB memory budget.

This build uses the fused base model GLM 5.2 with the L2 Coding LoRA from Macaron-V1-Venti.

Quantization (bpw)	Perplexity	Token Accuracy	Missed Divergence
Q4.5	1.35937	89.75%	28.98%
Q4.8	1.26562	93.50%	19.57%
Q4.8-INF	1.21093	97.70%	10.65%
Q5.5	1.24218	94.60%	17.55%
Q6.5	1.21875	96.85%	16.03%
Q8.5	1.21875	97.65%	9.92%
Base	1.20312	100.0%	0.000%

Perplexity: Measures the confidence for predicting base tokens (lower is better).
Token Accuracy: The percentage of correctly generated base tokens.
Missed Divergence: Measures severity of misses; how much the token was missed by.

Quantized with a modified version of MLX.

For more details see our demonstration videos or visit zai-org/GLM-5.2 and mindlab-research/Macaron-V1-Coding-Venti.

Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.

Downloads last month: 492

MLX

Hardware compatibility

Quantized

Model tree for inferencerlabs/Macaron-V1-Coding-Venti-MLX-Q4.8-INF

Base model

zai-org/GLM-5.2

Finetuned

(24)

this model