Audio GGUF models
1518 GGUF models: speech, music and audio models, which are not language models. Sizes run from 1M to 35.9B parameters. The longest trained context is 1024K tokens.
SI
Silero VAD
Silero · Serveurperso
Params—
Context—
Smallest0.0 GB
NE
nemotron 3.5 asr streaming 0.6b
Nemotron · myflow-ai
Params638M
Context—
Smallest0.8 GB
QW
qwen3 omni 30B a3b instruct
Qwen · DeepMentor
Params648M
Context—
Smallest0.1 GB
NE
Nemotron-3-Diarization.q8_0
Nemotron · SAIFIINDUSTRIES
Params99M
Context—
Smallest0.1 GB
ST
stt be fastconformer hybrid large pc
Stt · Pashted
Params120M
Context—
Smallest0.1 GB
PA
Paraformer
Paraformer · AIArchiveInfo
Params216M
Context—
Smallest0.2 GB
WH
Whisper Large v3
Whisper · tory-labs
Params1.54B
Context—
Smallest1.2 GB
CA
Canary 180M Flash
Canary · myflow-ai
Params189M
Context—
Smallest0.2 GB
PH
phonon 31m en
Phonon · eustlb
Params41M
Context—
Smallest0.1 GB
UN
underdog bark 3.0
Underdog · scholzmx
Params627M
Context—
Smallest0.4 GB
RU
RubaiSTT v2 Medium (Uzbek)
Rubaistt · nizom333
Params764M
Context—
Smallest0.8 GB
ST
stt ar fastconformer hybrid large pc v1.0
Stt · Pashted
Params120M
Context—
Smallest0.1 GB
FR
marblenet-vad-multilingual-v2
Frame · cstr
Params—
Context—
Smallest0.0 GB
SE
SenseVoice Small
Sensevoicesmall · willspeak
Params234M
Context—
Smallest0.2 GB
WH
Whisper Small (English)
Whisper · epapanita
Params242M
Context—
Q4_K_M0.2 GB
VO
VoxCPM2
Voxcpm · Enoxis
Params—
Context—
Smallest1.7 GB
QW
Qwen3-ASR-0.6B
Qwen · Sim382499488
Params938M
Context—
Smallest1.4 GB
FU
FunAudioLLM SenseVoiceSmall
Funaudiollm · Allinsama
Params234M
Context—
Smallest0.3 GB
SE
sensevoice small loom
Sensevoicesmall · loom-ai-org
Params234M
Context—
Smallest0.9 GB
QW
dolia tts qwen3 tts lora astarion
Qwen · A-walla-walla
Params19M
Context—
Smallest0.1 GB
CA
candle whisper
Candle · radames
Params38M
Context—
Smallest0.0 GB
QW
Qwen3-ASR 1.7B
Qwen · epapanita
Params2.04B
Context—
Q4_K_M1.3 GB
PA
Parakeet TDT-CTC 110M (CTC head)
Parakeet · dawsonvosburg
Params109M
Context—
Smallest0.2 GB
WH
Whisper Tiny
Whisper · voicetide
Params38M
Context—
Smallest0.0 GB
PA
Parakeet TDT 1.1B
Parakeet · epapanita
Params1.07B
Context—
Q4_K_M0.8 GB
MO
moss audio tokenizer v2 loom
Moss · loom-ai-org
Params1.08B
Context—
Smallest4.3 GB
CS
cstr htdemucs
Cstr · Allinsama
Params42M
Context—
Smallest0.0 GB
SE
SenseVoiceSmall GGUF audiocpp
Sensevoicesmall · AIArchiveInfo
Params234M
Context—
Smallest0.3 GB
QW
Canary-Qwen 2.5B
Qwen · myflow-ai
Params2.53B
Context—
Smallest2.0 GB
NE
ghira asr vi 0.6b
Nemotron · nhtera
Params648M
Context—
Smallest0.7 GB