GGUF models by memoravox
46 GGUF models quantized by memoravox on Hugging Face. Sizes run from 27M to 4.43B parameters.
NE
nemotron 3.5 asr streaming 0.6b
Nemotron · memoravox
Params638M
Context—
Smallest0.8 GB
WH
Whisper Large v3 Turbo
Whisper · memoravox
Params809M
Context—
Smallest0.9 GB
QW
Qwen3-ASR 0.6B
Qwen · memoravox
Params782M
Context—
Smallest0.9 GB
PA
Parakeet TDT 0.6B v3
Parakeet · memoravox
Params627M
Context—
Smallest0.7 GB
CA
Canary 180M Flash
Canary · memoravox
Params189M
Context—
Smallest0.2 GB
PA
Parakeet Unified EN 0.6B
Parakeet · memoravox
Params618M
Context—
Smallest0.7 GB
WH
Whisper Tiny
Whisper · memoravox
Params38M
Context—
Smallest0.0 GB
WH
Whisper Large
Whisper · memoravox
Params1.54B
Context—
Smallest1.2 GB
CA
Canary 1B v2
Canary · memoravox
Params980M
Context—
Smallest0.8 GB
GI
GigaAM v3 E2E-RNN-T
Gigaam · memoravox
Params223M
Context—
Smallest0.3 GB
WH
Whisper Small (English)
Whisper · memoravox
Params242M
Context—
Smallest0.3 GB
WH
Whisper Base
Whisper · memoravox
Params73M
Context—
Smallest0.1 GB
NE
Nemotron Speech Streaming EN
Nemotron · memoravox
Params618M
Context—
Smallest0.7 GB
WH
Whisper Tiny (English)
Whisper · memoravox
Params38M
Context—
Smallest0.0 GB
WH
Whisper Large v3
Whisper · memoravox
Params1.54B
Context—
Smallest1.2 GB
MI
Voxtral Mini 4B Realtime
Mistral · memoravox
Params4.43B
Context—
Smallest3.3 GB
GR
Granite Speech 4.1 2B
Granite · memoravox
Params2.31B
Context—
Smallest1.8 GB
WH
Whisper Base (English)
Whisper · memoravox
Params73M
Context—
Smallest0.1 GB
CO
Cohere Transcribe
Cohere · memoravox
Params2.05B
Context—
Smallest1.8 GB
GI
GigaAM v3 RNN-T
Gigaam · memoravox
Params222M
Context—
Smallest0.3 GB
WH
Whisper Small
Whisper · memoravox
Params242M
Context—
Smallest0.3 GB
PA
Parakeet TDT 0.6B v2
Parakeet · memoravox
Params618M
Context—
Smallest0.7 GB
WH
Whisper Large v2
Whisper · memoravox
Params1.54B
Context—
Smallest1.2 GB
PA
Parakeet TDT-CTC 1.1B
Parakeet · memoravox
Params1.07B
Context—
Smallest0.9 GB
CA
Canary 1B Flash
Canary · memoravox
Params890M
Context—
Smallest0.8 GB
WH
Whisper Medium (English)
Whisper · memoravox
Params764M
Context—
Smallest0.8 GB
GI
GigaAM v3 E2E-CTC
Gigaam · memoravox
Params221M
Context—
Smallest0.3 GB
QW
Qwen3-ASR 1.7B
Qwen · memoravox
Params2.04B
Context—
Smallest1.5 GB
WH
Whisper Medium
Whisper · memoravox
Params764M
Context—
Smallest0.8 GB
GR
granite 4.0 1b speech
Granite · memoravox
Params2.31B
Context—
Smallest1.8 GB
About memoravox on Hugging Face
memoravox has published 46 GGUF models that ggufmodels.com tracks, across families such as Whisper, Parakeet and Moonshine. The most downloaded are nemotron 3.5 asr streaming 0.6b, Whisper Large v3 Turbo and Qwen3-ASR 0.6B.
The quants memoravox publishes most often are Q8_0 (30) and Q5_K_M (16). Parameter counts run from 27M to 4.43B.
Frequently asked questions
What GGUF models has memoravox published?
46 models are listed here, mainly from the Whisper, Parakeet and Moonshine families. The most downloaded is nemotron 3.5 asr streaming 0.6b.
Which quants does memoravox publish?
The most common are Q8_0 (30 models) and Q5_K_M (16 models).