Blaizzy

"""
Benchmark TriAttention on MATH 500 — matching the paper's evaluation protocol.

Paper settings: max_tokens=32768, temp=0.6, top_p=0.95, budget=512/1024/2048
We use max_tokens=4096 for practical runtime on Apple Silicon.

USAGE
    python bench_triattention_math.py \
        --model /tmp/gemma-4-26b-a4b-it-5bit \
        --calib /tmp/gemma4_26b_5bit_calib.safetensors \

Blaizzy

"""
Benchmark TurboQuant (TBQ) vs baseline on MM-NIAH (Multimodal Needle-in-a-Haystack).

INSTALL
    pip install -U mlx-vlm
    # or
    uv pip install -U mlx-vlm

SETUP — Extract images (one-time)
    huggingface-cli download OpenGVLab/MM-NIAH mm_niah_val/images.tar.gz --repo-type dataset

Blaizzy

"""Benchmark TurboQuant vs baseline on LongBench-v2.

Usage:
    python scripts/bench_longbench_v2.py --model google/gemma-4-e4b-it --num-samples 10 --max-tokens-ctx 260000
    python scripts/bench_longbench_v2.py --model google/gemma-4-26b-a4b-it --num-samples 5 --max-tokens-ctx 128000 --kv-bits 4
"""

import argparse
import importlib
import time

Blaizzy

#!/usr/bin/env python3
"""
Benchmark for Qwen3-TTS: measures TTFB, inter-chunk latency, and throughput.

Usage:                                                                                                                                                                                
  # Sequential only (short/medium/long)                                                                                                                                                                 
  python qwen3_tts_benchmark.py --model mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16

  # Sequential + batched (1,2,3,4,8)
  python qwen3_tts_benchmark.py --batch-size 1 2 3 4 8

Blaizzy

#!/usr/bin/env python3
"""
Benchmark for Qwen3-TTS: measures TTFB, inter-chunk latency, and throughput.

Usage:
    python benchmarks/qwen3_tts_benchmark.py
    python benchmarks/qwen3_tts_benchmark.py --model mlx-community/Qwen3-TTS-0.6B-bf16
    python benchmarks/qwen3_tts_benchmark.py --num-trials 3 --streaming-interval 1.0
    python benchmarks/qwen3_tts_benchmark.py --prompts short medium long
"""

Blaizzy

Qwen3-TTS Batch Generation Benchmark Results

Voice: serena Device: Apple Silicon (MLX) Date: 2025-02-28

---

Cross-Model Comparison (batch=4, short prompt)

Blaizzy

//
//  BaseConfiguration.swift
//  mlx-test
//
//  Created by Prince Canuma on 29/12/25.
//

import Foundation
import MLX

Blaizzy

mlx_audio.tts.generate \
  --model mlx-community/chatterbox-turbo-fp16 \
  --text 'Abstract
The dominant sequence transduction models are based on complex recurrent or
convolutional neural networks that include an encoder and a decoder. The best
performing models also connect the encoder and decoder through an attention
mechanism. We propose a new simple network architecture, the Transformer,
based solely on attention mechanisms, dispensing with recurrence and convolutions
entirely. Experiments on two machine translation tasks show these models to
be superior in quality while being more parallelizable and requiring significantly

Blaizzy

#!/usr/bin/env python3
# Copyright (c) 2025 Resemble AI
# MIT License
# Weight conversion script: PyTorch -> MLX

"""
Converts Chatterbox Turbo weights from PyTorch to MLX format.

Usage:
    python convert_weights.py --output model.safetensors

Blaizzy

import json
from functools import partial
from json import JSONDecodeError
from typing import List

from transformers import AutoTokenizer
import tokenizers

REPLACEMENT_CHAR = "\ufffd"