Instructions to use leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-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("leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-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 leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-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 "leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-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": "leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-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 "leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-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 leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-mlx

Run Hermes

hermes

MLX LM

How to use leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-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 "leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Huihui-Qwen3.6-35B-A3B-abliterated (6-bit MLX)

This is a quantized version of huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated for Apple Silicon using MLX.

Quantization Details

Format: MLX (Apple Silicon)
Architecture: Qwen3.6 MoE (Mixture of Experts) — text-only
Bits per weight: 6.642
Total size: ~27 GB
Group size: 64
Quantization mode: affine

Mixed Quantization Strategy

Layer type	Bits
Embeddings (embed_tokens, lm_head)	8-bit
Attention (self_attn, linear_attn)	8-bit
MoE Router (mlp.gate)	8-bit
Shared Expert + Gate	8-bit
Routed Experts (switch_mlp)	6-bit
All other layers	8-bit

Usage

from mlx_lm import load, generate

model, tokenizer = load("leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-mlx")
response = generate(model, tokenizer, prompt="Hello!", verbose=True)