The smallest-footprint build: peak RSS 1.85 GB (Q4_0), fits a 4 GB host, and loads directly in whisper.cpp desktop apps (MacWhisper Pro, superwhisper) — drag the .bin in, no code. Slower than CT2 (RTF 0.40) but the RAM floor is 1 GB lower.

(Files are whisper.cpp GGML format. whisper.cpp GGUF support is in progress upstream, ggml-org/whisper.cpp#3316; GGUF builds will be added when the toolchain lands.)

Part of the Breeze-ASR-26 edge family — the same MediaTek model in every runtime, pick by your constraint:

Repo Runtime RSS RTF (CPU 4-thread) Best for
Breeze-ASR-26-ct2 CTranslate2 / faster-whisper ~2.9 GB 0.21 servers, 8 GB+ hosts, GPU
Breeze-ASR-26-GGML whisper.cpp / MacWhisper 1.85 GB 0.40 4 GB hosts, desktop apps
Breeze-ASR-26-ONNX sherpa-onnx / onnxruntime — 1.3 Android / iOS / WASM

All Apache-2.0, derived from MediaTek-Research/Breeze-ASR-26. Measured on real multi-speaker Mandarin meeting audio. Mandarin does not regress; Taigi is transcribed as Mandarin meaning (not verbatim Taigi characters).

Usage

bash

# whisper.cpp
whisper-cli -m breeze-q5_0.bin -f meeting.wav -l zh -t 4

MacWhisper Pro / superwhisper: download breeze-q5_0.bin, drag it in as a custom model.

Build	Disk	Peak RSS	RTF
Q4_0	848 MB	1.85 GB	0.40
Q5_0	1.1 GB	2.03 GB	0.62

Repo	Runtime	RSS	RTF (CPU 4-thread)	Best for
Breeze-ASR-26-ct2	CTranslate2 / faster-whisper	~2.9 GB	0.21	servers, 8 GB+ hosts, GPU
Breeze-ASR-26-GGML	whisper.cpp / MacWhisper	1.85 GB	0.40	4 GB hosts, desktop apps
Breeze-ASR-26-ONNX	sherpa-onnx / onnxruntime	—	1.3	Android / iOS / WASM

weemed/Breeze-ASR-26-GGML

Breeze-ASR-26 — GGML (whisper.cpp, Q4_0 / Q5_0)

Usage

weemed/
Breeze-ASR-26-GGML