CoolFace
Modelpublic

Atomic-Germ/BigBang1.0-35B-A3B-NPU2

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face
0likes659downloads
Model Card

IF YOU USE COMMUNITY QWEN MODELS DO NOT UPGRADE TO FLM v1.0.2+

About

Q4NX for FastFlowLM (AMD Ryzen AI XDNA2) quant of https://huggingface.co/endless-frontier/BigBang-v1

What is Q4NX?

Q4NX is FastFlowLM's native packed-quantization format - a rearranged Q4_1 layout tuned for the NPU matrix engine's tile sizes and memory access patterns. It is not a GGUF file and it does not run on llama.cpp or Ollama; it is meant exclusively for the FastFlowLM engine on AMD Ryzen AI NPUs.

Requirements

  • —FastFlowLM >= 0.9.45 (flm CLI)
  • —AMD Ryzen AI processor with XDNA2 (NPU2) - Strix Point / Ryzen AI 300 series or later
  • —XRT NPU stack installed
  • —>32 GB of unified system memory (Q4NX weights + activations + KV cache)

Files

FilePurpose
model.q4nxQuantized Q4NX weights
config.jsonFastFlowLM model configuration
tokenizer.jsonTokenizer
tokenizer_config.jsonSpecial tokens and chat template
chat_template.jinjaChat template (optional)
flm-add.pyInstaller script - registers this model with FastFlowLM

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

bash
uv tool install flm-add
flm-add Atomic-Germ/BigBang1.0-35B-A3B-NPU2 --family qwen3.6-moe --tag bigbang1.0-moe:35b-a3b
FLM_XCLBIN_PATH="$HOME/.config/flm" FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" flm run bigbang1.0-moe:35b-a3b

Kernels

FastFlowLM's NPU kernels (xclbins) are closed source and are not shipped in this repository. flm-add.py links the kernels of the official `qwen3.6-moe:35b-a3b` model (Qwen3.6-35B-A3B-NPU2), because this model shares the same engine family (qwen3.6-moe) and architecture.

Model

  • —Registry tag: bigbang1.0-moe:35b-a3b
  • —Engine family: qwen3.6-moe
  • —Kernel source: Qwen3.6-35B-A3B-NPU2

Original model card

See the upstream model card for training details, benchmarks, and upstream usage. This repository only contains the Q4NX conversion for FastFlowLM.