How to use from
OpenClaw
Start the llama.cpp server
# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Atomic-Germ/Qwable-Claude-Fable-5-Distilled-NPU2:Q8_0
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://127.0.0.1:9931/v1 \
  --custom-model-id "Atomic-Germ/Qwable-Claude-Fable-5-Distilled-NPU2:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Quick Links

Qwable-Claude-Fable-5-Distilled-NPU2

FastFlowLM Q4NX conversion of empero-ai/Qwable-9B-Claude-Fable-5 for AMD XDNA NPU inference.

This repository contains a quantized Q4NX port of the model, compiled for the FastFlowLM (FLM) runtime. It is not a GGUF file.

Item Value
Source model empero-ai/Qwable-9B-Claude-Fable-5
Weights model.q4nx (7.11 GB)
Modality language / vision
FLM version 1.0.1
Converted 2026-08-27

Install and run

This repository works with flm-add, a small installer that copies the model into the FastFlowLM user directory and registers the tag. It never modifies the system FastFlowLM install.

pip install flm-add or uv tool install flm-add

uv tool install flm-add
flm-add Atomic-Germ/Qwable-Claude-Fable-5-Distilled-NPU2 --family qwen3.5 --tag qwable-claude-fable-5-distilled:9b
FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" FLM_XCLBIN_PATH="$HOME/.config/flm" flm run qwable-claude-fable-5-distilled:9b

Files

File Description
model.q4nx Quantized weights (Q8_0 / Q4_1 / BF16)
config.json FLM runtime configuration
tokenizer.json Tokenizer vocabulary
tokenizer_config.json Tokenizer configuration
chat_template.jinja Chat template
vision_weight.q4nx Vision model

Source model card

See the original model card: empero-ai/Qwable-9B-Claude-Fable-5 on Hugging Face

Downloads last month
549
GGUF
Model size
9B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Atomic-Germ/Qwable-Claude-Fable-5-Distilled-NPU2

Finetuned
Qwen/Qwen3.5-9B
Quantized
(16)
this model

Dataset used to train Atomic-Germ/Qwable-Claude-Fable-5-Distilled-NPU2