Instructions to use shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit 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("shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit")

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 shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit"

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": "shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit 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 "shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit"

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 shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit

Run Hermes

hermes

MLX LM

How to use shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Base model artwork

Qwen-9B-Claude-Fable-5-1M-MLX-8bit

An 8-bit MLX quantization of empero-ai/Qwythos-9B-Claude-Mythos-5-1M, published as Qwen-9B-Claude-Fable-5-1M-MLX-8bit and optimized for Apple Silicon.

Model Details

Base model: empero-ai/Qwythos-9B-Claude-Mythos-5-1M
Architecture: Qwen 3.5 (32 layers, 4096 hidden, 16 heads, 4 KV heads)
Quantization: 8-bit affine, group size 64
Context length: 1M tokens (native)
Model size: ~9.52 GB (safetensors)

Usage (MLX)

sfw pip install mlx-lm

Remove sfw if you don't have sfw from Socket installed. It's free and an improvement over running pip or npm raw.

from mlx_lm import load, generate

model, tokenizer = load("shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit")
response = generate(model, tokenizer, prompt="Hello!", max_tokens=256)
print(response)

Benchmarks

See base model card for evaluation results.

License

Apache 2.0 — same as the base model.

Downloads last month: 523

Safetensors

Model size

9B params

Tensor type

BF16

U32

MLX

Hardware compatibility

8-bit

Model tree for shamsghi/Qwen-9B-Claude-Fable-5-1M-MLX-8bit

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

empero-ai/Qwythos-9B-Claude-Mythos-5-1M

Quantized

(32)

this model