Skip to content
ModelListedExternal
Download

Whisper Tiny GGUF

Run fast, fully local speech-to-text dictation in Unsloth Studio. Whisper Tiny has the lowest download size and memory use in the default Whisper lineup, making it the fastest option for short everyday dictation.

Sourcehuggingface.co/unslothai/whisper-tiny-GGUF/tree/391c60735633e8ee326e927d295b37ad9aae030d
KindOtherBase modelunslothai/whisper-tinyVersionWhisper tinyCgrade

Model source

Kind
Other
File size
74.1 MB
Base model
unslothai/whisper-tiny
Version
vWhisper tiny
Updated
Oct 31, 2026
Source
Hugging Face

Source description

Whisper Tiny F16 for Unsloth Studio

Run fast, fully local speech-to-text dictation in Unsloth Studio. Whisper Tiny has the lowest download size and memory use in the default Whisper lineup, making it the fastest option for short everyday dictation.

Run in Unsloth Studio

  1. Install or update Unsloth Studio.
  2. Open Settings > Voice.
  3. Open the local dictation model picker and select Whisper Tiny.
  4. Let Studio download and cache the model.
  5. 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-tiny.bin: native F16 model for whisper.cpp
  • Download size: approximately 78 MB
  • Best for: fastest startup, lowest memory use, and short dictation

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-tiny.bin -f audio.wav

Integrity

  • Source model.safetensors SHA-256: 7ebd0e69e78190ffe1438491fa05cc1f5c1aa3a4c4db3bc1723adbb551ea2395
  • Converted model SHA-256: bf4711d269a0c0bc7d8411fc2d78d4c6727a215406da46c42975e15684b01746
  • Conversion tool: ggml-org/whisper.cpp commit 080bbbe85230f624f0b52127f1ae1218247989f9

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

Sources

1 source
Hugging FacePrimaryVersion 391c60735633e8ee326e927d295b37ad9aae030d
huggingface.co/unslothai/whisper-tiny-GGUF/tree/391c60735633e8ee326e927d295b37ad9aae030d

Verified Oct 31

Model artifacts

1 artifact

whisper-tiny.bin

bin · 74.1 MB · SHA-256 bf4711d269a0…1746 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 15huggingface.co/unslothai/whisper-tiny-GGUF

--- base_model: unslothai/whisper-tiny license: apache-2.0 library_name: whisper.cpp pipeline_tag: automatic-speech-recognition tags: - whisper - whisper.cpp - ggml - f16 - unsloth-studio - unsloth --- # Whisper Tiny F16 for Unsloth Studio Run fast, fully local speech-to-text dictation in [Unsloth Studio](https://unsloth.ai/docs). Whisper Tiny has the lowest download size and memory use in the default Whisper lineup, making it the fastest option for short everyday dictation. ## Run in Unsloth Studio 1. Install or update [Unsloth Studio](https://unsloth.ai/docs). 2. Open **Settings > Voice**. 3. Open the local dictation model picker and select **Whisper Tiny**. 4. Let Studio download and cache the model. 5. 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-tiny.bin`: native F16 model for `whisper.cpp` - Download size: approximately 78 MB - Best for: fastest startup, lowest memory use, and short dictation `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 ```bash whisper-cli -m whisper-tiny.bin -f audio.wav ``` ## Integrity - Source `model.safetensors` SHA-256: `7ebd0e69e78190ffe1438491fa05cc1f5c1aa3a4c4db3bc1723adbb551ea2395` - Converted model SHA-256: `bf4711d269a0c0bc7d8411fc2d78d4c6727a215406da46c42975e15684b01746` - Conversion tool: `ggml-org/whisper.cpp` commit `080bbbe85230f624f0b52127f1ae1218247989f9` The converted model was loaded by `whisper.cpp` and passed an end-to-end transcription test.

NoteAug 15huggingface.co/unslothai/whisper-tiny-GGUF

Source context: 0 downloads · 0 likes · Pipeline automatic-speech-recognition · Library whisper.cpp · Repo unslothai/whisper-tiny-GGUF