Instructions to use khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6 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("khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6")

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 khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6"

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": "khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6 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 "khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6"

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 khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6"

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 "khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6" \
  --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"

Qwen3.6-14B-A3B-FableVibes-mlx-q6

MLX 6-bit quantization of tvall43/Qwen3.6-14B-A3B-FableVibes, for local inference on Apple Silicon.

Credit / original model

This repo is only a quantized MLX conversion. All credit for the model itself goes to the original author, tvall43. Please see and cite the original model card.

The base is a REAP-pruned Qwen3.6-35B-A3B reduced to ~14B total / ~3B active (90 experts, 8 active), recovered with a QLoRA distill of Claude Fable 5 reasoning traces. It uses the Qwen3.5 hybrid architecture (GatedDeltaNet linear attention + full attention + MoE) and emits <think>...</think> reasoning.

What this conversion did

Fused the routed-MoE experts from per-expert tensors (experts.{i}.{gate,up,down}_proj) into mlx-lm's stacked experts.gate_up_proj / experts.down_proj format.
Quantized to 6-bit, group size 64 with mlx-lm.
~10 GB; runs on a 16 GB Apple Silicon Mac.

Usage

uv run python -m mlx_lm generate \
  --model khanh2023/Qwen3.6-14B-A3B-FableVibes-mlx-q6 \
  --prompt "Solve: ..."

Notes

MoE sparsity (~~3B active/token) makes decode fast (~~46 tok/s on an M4) despite 14B total params.
6-bit preserves more exactness than q4 on strict reasoning, at ~10 GB (needs a raised Metal wired limit on 16 GB). A smaller -mlx-q4 variant is also available.