Phox — BQSM Ternary Model Weights
Model weights for the Phox BQSM (Basin-Quotient-Machine) wave-rider inference engine.
Overview
This repository contains ternary-quantized model weights for the Phoenix Brain — a Kuramoto oscillator interference engine that performs inference through traveling wave activation rather than traditional matrix multiplication.
Architecture
Engine : Phoenix Brain (phoenix_brain.c) — 4-ring Kuramoto core + demand-driven tendrilsWeights : 4-level ternary quantization (80% sparsity, 2 bits per weight)Compute : AVX2 SIMD + OpenMP parallelism (CPU only)No GPU required : Engine is pure C with AVX2, runs on any x86-64 CPU
Models
File Size Description gemma4-12b-ternary-normed.bqsm2.8GB Gemma-4-12B ternary weights (normalized) gemma4-12b-bf16-ternary.bqsm1.2GB Gemma-4-12B BF16-derived ternary gemma4-12b.vocab2.8MB Token vocabulary hermes-3b-ternary.bqsm766MB Hermes-3-3B ternary weights hermes-3b.vocab1.3MB Token vocabulary phoenix-evolved.pbrain~2MB Evolved brain state file
Files
gemma4-12b-ternary-normed.bqsm — Main 12B parameter model with normalized weightstokenizer/ — Gemma 4 tokenizer files (compatible with HuggingFace transformers)gemma4-12b.vocab — Token-to-ID vocabulary mapping for the C engine
Usage
Compile the engine:
cc -O3 -std=c11 -march=native -fopenmp phoenix_brain.c -o phoenix -lmRun inference:
./phoenix gemma4-12b-ternary-normed.bqsm 20Chat mode (with ring buffer I/O):
./phoenix gemma4-12b-ternary-normed.bqsm --chatPerformance
~4.9 tok/s on 12B model (12-core CPU, AVX2)
Model loaded via mmap (no RAM duplication)
48 layers of wave-rider physics per token
Citation
If you use this work, please reference:
Nicholas Bumgarner, emerging.systems
"Basin-Quotient-Machine: Cross-Harmonic Computation"
