Whisper GGUF models

134 GGUF models in the Whisper family, quantized by 42 uploaders. Sizes run from 30M to 1.61B parameters.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
WH
Whisper Medium
Whisper · handy-computer
Params764M
Context—
Q4_K_M0.5 GB
GGUF
WH
Whisper Large v3 Turbo
Whisper · handy-computer
Params809M
Context—
Q4_K_M0.5 GB
GGUF
WH
Whisper Large v3
Whisper · handy-computer
Params1.54B
Context—
Q4_K_M1.0 GB
GGUF
WH
Whisper Small
Whisper · handy-computer
Params242M
Context—
Q4_K_M0.2 GB
GGUF
WH
Whisper Large
Whisper · handy-computer
Params1.54B
Context—
Q4_K_M1.0 GB
GGUF
WH
Whisper Large v2
Whisper · handy-computer
Params1.54B
Context—
Q4_K_M1.0 GB
GGUF
WH
whisper large v3 turbo
Whisper · xkeyC
Params809M
Context—
Smallest0.5 GB
GGUF
WH
Whisper Medium (English)
Whisper · handy-computer
Params764M
Context—
Q4_K_M0.5 GB
GGUF
WH
Whisper Base
Whisper · handy-computer
Params73M
Context—
Q4_K_M0.1 GB
GGUF
WH
Whisper Small (English)
Whisper · handy-computer
Params242M
Context—
Q4_K_M0.2 GB
GGUF
WH
Whisper Tiny
Whisper · handy-computer
Params38M
Context—
Q4_K_M0.0 GB
GGUF
WH
whisper tiny
Whisper · FL33TW00D-HF
Params38M
Context—
Smallest0.0 GB
GGUF
WH
whisper tiny
Whisper · oxide-lab
Params38M
Context—
Smallest0.0 GB
GGUF
WH
whisper large v3 turbo
Whisper · oxide-lab
Params809M
Context—
Smallest0.3 GB
GGUF
WH
Whisper Base (English)
Whisper · handy-computer
Params73M
Context—
Q4_K_M0.1 GB
GGUF
WH
Whisper Tiny (English)
Whisper · handy-computer
Params38M
Context—
Q4_K_M0.0 GB
GGUF
WH
whisper base
Whisper · oxide-lab
Params73M
Context—
Smallest0.0 GB
GGUF
WH
whisper small
Whisper · FL33TW00D-HF
Params242M
Context—
Smallest0.1 GB
GGUF
WH
whisper medium
Whisper · OllmOne
Params764M
Context—
Smallest0.4 GB
GGUF
WH
whisper medium
Whisper · oxide-lab
Params764M
Context—
Smallest0.3 GB
GGUF
WH
whisper small
Whisper · oxide-lab
Params242M
Context—
Smallest0.1 GB
GGUF
WH
whisper large v3
Whisper · vonjack
Params1.6B
Context—
Smallest1.7 GB
GGUF
WH
whisper base
Whisper · FL33TW00D-HF
Params73M
Context—
Smallest0.0 GB
GGUF
WH
psiuu
Whisper · llaosdigital
Params627M
Context—
Smallest0.7 GB
GGUF
WH
whisper large v3
Whisper · OllmOne
Params1.54B
Context—
Smallest0.9 GB
GGUF
WH
Whisper Large v3 Turbo
Whisper · voconly-org
Params809M
Context—
Q4_K_M0.5 GB
GGUF
WH
whisper large v3
Whisper · oxide-lab
Params1.61B
Context—
Smallest0.5 GB
GGUF
WH
whisper vad encdec asmr
Whisper · cstr
Params30M
Context—
Smallest0.0 GB
GGUF
WH
whisper large v3 turbo
Whisper · Xviers
Params809M
Context—
Smallest0.3 GB
GGUF
WH
zubr whisper
Whisper · alekringtonnn-ai
Params250M
Context—
Smallest0.1 GB
GGUF

About the Whisper GGUF models

Whisper is represented on ggufmodels.com by 134 GGUF models, quantized by 42 uploaders on Hugging Face. The most downloaded are Whisper Medium, Whisper Large v3 Turbo and Whisper Large v3. Parameter counts run from 30M to 1.61B.

A Q4_K_M file of a Whisper model is between 0.0 to 1.0 GB, which is the quant most people start with. Most files come from voicetide (12), myflow-ai (12) and memoravox (12). The quants you will meet most often are Q8_0 (96), Q5_K_M (38), F16 (37) and Q6_K (33), where the number is how many models offer that quant.

Frequently asked questions

Which Whisper GGUF should I download?

The most downloaded Whisper GGUF here is Whisper Medium. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Whisper model need?

Q4_K_M files of Whisper models on this site range from 0.0 to 1.0 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Whisper GGUF files come from?

The most common quantizers here are voicetide, myflow-ai and memoravox. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing