Whisper Large v3 Turbo F16 for Unsloth Studio

Run high-quality, fully local speech-to-text dictation in Unsloth Studio. Whisper Large v3 Turbo offers the strongest speed and accuracy balance in the default Whisper lineup and is the recommended choice for capable hardware.

Run in Unsloth Studio

Install or update Unsloth Studio.
Open Settings > Voice.
Open the local dictation model picker and select Whisper Large v3 Turbo.
Let Studio download and cache the model.
Use the microphone button in the chat composer to dictate locally.

The model runs on your device through whisper.cpp. Your recorded audio does not need to be sent to a hosted transcription service.

Model file

whisper-large-v3-turbo.bin: native F16 model for whisper.cpp
Download size: approximately 1.62 GB
Best for: the recommended balance of high accuracy and fast transcription

whisper.cpp uses a custom GGML binary format for Whisper. The model file is therefore named .bin, not .gguf, even though this repository follows the common -GGUF repository naming convention.

No low-bit quantization was applied. Matrix weights are stored as F16, while tensors that whisper.cpp requires in F32 remain F32.

Manual whisper.cpp usage

whisper-cli -m whisper-large-v3-turbo.bin -f audio.wav

Integrity

Source model.safetensors SHA-256: 542566a422ae4f3fd23f1ba11add198fca01bbf82e66e6a2857b3f608b1eb9d1
Converted model SHA-256: 0dc8bab01bd6b0ab68e8ebb607bf3c960ff1bc136644a23b3ad59f7c00e78d09
Conversion tool: ggml-org/whisper.cpp commit 080bbbe85230f624f0b52127f1ae1218247989f9

The converted model was loaded by whisper.cpp and passed an end-to-end transcription test.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for unslothai/whisper-large-v3-turbo-GGUF

Base model

unslothai/whisper-large-v3-turbo

Finetuned

(1)

this model