GGUF models by cstr

462 GGUF models quantized by cstr on Hugging Face. Sizes run from 1M to 10.7B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
AR
ark asr 3b
Ark · cstr
Params3.75B
Context—
Smallest0.0 GB
GGUF
QW
qwen3 tts 0.6b customvoice
Qwen · cstr
Params906M
Context—
Smallest1.0 GB
GGUF
QW
qwen3-tts-tokenizer-12hz
Qwen · cstr
Params162M
Context—
Smallest0.3 GB
GGUF
BR
breeze-tts-2
Breeze · cstr
Params2.85B
Context—
Smallest2.2 GB
GGUF
FU
Fun-CosyVoice3-0.5B-2512-voices
Fun · cstr
Params7M
Context—
Smallest0.0 GB
GGUF
QW
qwen3 tts 1.7b customvoice
Qwen · cstr
Params1.92B
Context—
Smallest2.0 GB
GGUF
QW
qwen3 asr 1.7b
Qwen · cstr
Params2.35B
Context—
Smallest1.5 GB
GGUF
PA
parakeet tdt 0.6b v3
Parakeet · cstr
Params627M
Context—
Smallest0.4 GB
GGUF
CO
Cohere Transcribe 03-2026
Cohere · cstr
Params2.07B
Context—
Smallest1.3 GB
GGUF
IN
index echo 2b
Index · cstr
Params1.88B
Context—
Smallest0.7 GB
GGUF
IN
index echo 9b
Index · cstr
Params8.95B
Context—
Smallest1.3 GB
GGUF
MU
multilingual e5 small
Multilingual · cstr
Params118M
Context512
Smallest0.1 GB
Embedding
FI
FireRedPunc
Fireredpunc · cstr
Params102M
Context—
Smallest0.1 GB
GGUF
CH
chatterbox
Chatterbox · cstr
Params264M
Context—
Smallest0.0 GB
GGUF
QW
qwen3 forced aligner 0.6b
Qwen · cstr
Params918M
Context—
Smallest0.5 GB
GGUF
MA
madlad400 3b mt
Madlad · cstr
Params2.94B
Context—
Smallest0.0 GB
GGUF
MO
MOSS Audio 4B Instruct
Moss · cstr
Params5.22B
Context—
Smallest0.0 GB
GGUF
QW
qwen3 asr 0.6b
Qwen · cstr
Params938M
Context—
Smallest0.0 GB
GGUF
CA
canary ctc aligner
Canary · cstr
Params626M
Context—
Smallest0.4 GB
GGUF
QW
qwen3 tts 1.7b voicedesign
Qwen · cstr
Params1.92B
Context—
Smallest2.0 GB
GGUF
QW
qwen3 tts 0.6b base
Qwen · cstr
Params915M
Context—
Smallest0.5 GB
GGUF
VO
voxcpm2
Voxcpm · cstr
Params2.38B
Context—
Smallest0.0 GB
GGUF
MI
voxtral mini 4b realtime
Mistral · cstr
Params4.43B
Context—
Smallest2.5 GB
GGUF
MI
mimo asr
Mimo · cstr
Params8.02B
Context—
Smallest0.0 GB
GGUF
VI
vibevoice asr
Vibevoice · cstr
Params8.33B
Context—
Smallest0.0 GB
GGUF
KO
kokoro voices
Kokoro · cstr
Params—
Context—
Smallest0.0 GB
GGUF
CO
confucius4 tts
Confucius · cstr
Params112M
Context—
Smallest0.1 GB
GGUF
SE
SenseVoiceSmall
Sensevoicesmall · cstr
Params234M
Context—
Smallest0.1 GB
GGUF
PA
parakeet tdt 0.6b ja
Parakeet · cstr
Params623M
Context—
Smallest0.4 GB
GGUF
QW
qwen3 tts 1.7b base
Qwen · cstr
Params1.93B
Context—
Smallest2.1 GB
GGUF

About cstr on Hugging Face

cstr has published 462 GGUF models that ggufmodels.com tracks, across families such as Opus, Stt and Qwen. The most downloaded are ark asr 3b, qwen3 tts 0.6b customvoice and qwen3-tts-tokenizer-12hz.

The quants cstr publishes most often are Q4_K (312), Q8_0 (306), F16 (252) and IQ4_XS (65). Their Q4_K_M files range from 0.8 to 5.3 GB. Parameter counts run from 1M to 10.7B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has cstr published?

462 models are listed here, mainly from the Opus, Stt and Qwen families. The most downloaded is ark asr 3b.

Which quants does cstr publish?

The most common are Q4_K (312 models), Q8_0 (306 models), F16 (252 models) and IQ4_XS (65 models).

Keep browsing