GGUF models by loom-ai-org

59 GGUF models quantized by loom-ai-org on Hugging Face. Sizes run from 1M to 4.19B parameters.

Most downloadedNewestLargestLongest contextSmallest
FU
fun cosyvoice3 0.5b loom
Fun · loom-ai-org
Params861M
Context—
Smallest3.4 GB
GGUF
GE
gemma 3 270m it loom
Gemma · loom-ai-org
Params268M
Context—
Smallest1.1 GB
GGUF
LF
lfm2.5 audio 1.5b tts loom
Lfm · loom-ai-org
Params1.38B
Context—
Smallest0.0 GB
GGUF
GR
granite speech 4.0 1b loom
Granite · loom-ai-org
Params2.19B
Context—
Smallest8.8 GB
GGUF
QW
qwen3 asr 0.6b loom
Qwen · loom-ai-org
Params783M
Context—
Smallest3.1 GB
GGUF
AU
audio8 tts realistic 0.6b loom
Audio · loom-ai-org
Params605M
Context—
Smallest0.7 GB
GGUF
WA
wakehubert tiny loom
Wakehubert · loom-ai-org
Params—
Context—
Smallest0.0 GB
GGUF
CA
canary 1b v2 loom
Canary · loom-ai-org
Params973M
Context—
Smallest3.9 GB
GGUF
ST
conformer ctc small loom
Stt · loom-ai-org
Params15M
Context—
Smallest0.1 GB
GGUF
LF
lfm2.5 audio 1.5b asr loom
Lfm · loom-ai-org
Params1.29B
Context—
Smallest5.2 GB
GGUF
SU
supertonic 2 loom
Supertonic · loom-ai-org
Params67M
Context—
Smallest0.3 GB
GGUF
QW
qwen3 tts 12hz 0.6b loom
Qwen · loom-ai-org
Params1.03B
Context—
Smallest4.1 GB
GGUF
MO
moss tts local transformer v1.5 loom
Moss · loom-ai-org
Params4.19B
Context—
Smallest16.8 GB
GGUF
CH
chatterbox loom
Chatterbox · loom-ai-org
Params670M
Context—
Smallest2.7 GB
GGUF
TT
f5 tts v1 base loom
Tts · loom-ai-org
Params356M
Context—
Smallest1.4 GB
GGUF
WH
whisper small loom
Whisper · loom-ai-org
Params242M
Context—
Smallest1.0 GB
GGUF
KO
kokoro 82m loom
Kokoro · loom-ai-org
Params81M
Context—
Smallest0.3 GB
GGUF
MA
matcha tts ljspeech loom
Matcha · loom-ai-org
Params32M
Context—
Smallest0.1 GB
GGUF
SP
speecht5 tts loom
Speecht · loom-ai-org
Params159M
Context—
Smallest0.0 GB
GGUF
MO
moonshine streaming small loom
Moonshine · loom-ai-org
Params123M
Context—
Smallest0.5 GB
GGUF
VO
voxcpm2 loom
Voxcpm · loom-ai-org
Params2.33B
Context—
Smallest9.3 GB
GGUF
NE
nemotron labs unified asr 0.6b loom
Nemotron · loom-ai-org
Params637M
Context—
Smallest0.7 GB
GGUF
PA
parakeet tdt 0.6b loom
Parakeet · loom-ai-org
Params637M
Context—
Smallest2.5 GB
GGUF
MO
moonshine streaming tiny loom
Moonshine · loom-ai-org
Params34M
Context—
Smallest0.1 GB
GGUF
ST
citrinet 256 ls loom
Stt · loom-ai-org
Params10M
Context—
Smallest0.0 GB
GGUF
GI
gigaam v3 rnnt loom
Gigaam · loom-ai-org
Params223M
Context—
Smallest0.9 GB
GGUF
FL
flan t5 small loom
Flan · loom-ai-org
Params77M
Context—
Smallest0.3 GB
GGUF
ST
styletts2 ljspeech loom
Styletts · loom-ai-org
Params103M
Context—
Smallest0.4 GB
GGUF
ST
citrinet 1024 loom
Stt · loom-ai-org
Params141M
Context—
Smallest0.6 GB
GGUF
PA
parakeet rnnt 0.6b loom
Parakeet · loom-ai-org
Params627M
Context—
Smallest2.5 GB
GGUF

About loom-ai-org on Hugging Face

loom-ai-org has published 59 GGUF models that ggufmodels.com tracks, across families such as Stt, Qwen and Lfm. The most downloaded are fun cosyvoice3 0.5b loom, gemma 3 270m it loom and lfm2.5 audio 1.5b tts loom.

The quants loom-ai-org publishes most often are Q8_0 (7), F32 (7), Q4_1 (1) and F16 (1). Parameter counts run from 1M to 4.19B.

Frequently asked questions

What GGUF models has loom-ai-org published?

59 models are listed here, mainly from the Stt, Qwen and Lfm families. The most downloaded is fun cosyvoice3 0.5b loom.

Which quants does loom-ai-org publish?

The most common are Q8_0 (7 models), F32 (7 models), Q4_1 (1 models) and F16 (1 models).

Keep browsing