Jahaz
/

Qwen3-tts-0.6b-gguf-for-koboldcpp

Model card Files Files and versions

Qwen3-tts-0.6b-gguf-for-koboldcpp

Ctrl+K

Ctrl+K

1 contributor

History: 28 commits

Jahaz's picture

Update README.md

114c17c verified about 1 month ago

.gitattributes

2.04 kB
MXFP4 wavtokenizer about 1 month ago
Qwen3-tts-0.6b-q8_0..gguf

986 MB
xet

requantized qwen3-tts-0.6b-q8_0.gguf about 2 months ago
README.md

1.01 kB
Update README.md about 1 month ago
qwen3-tts-0.6b-MXFP4.gguf

505 MB
xet

update mxfp4 for faster speed about 1 month ago
qwen3-tts-0.6b-iq4_xs.gguf

505 MB
xet

qwen3-tts-o.6b-Iq4xs.gguf about 2 months ago
qwen3-tts-0.6b-q5k.gguf

663 MB
xet

better quality than iq4xs in long transcript about 1 month ago
qwen3-tts-tokenizer-MXFP4.gguf

198 MB
xet

MXFP4 wavtokenizer about 1 month ago
qwen3-tts-tokenizer-iq3s.gguf

203 MB
xet

Part of tensor be quanted to iq3s. about 2 months ago
qwen3-tts-tokenizer-iq4_xs-v2.gguf

211 MB
xet

Smaller tokenizer about 2 months ago
qwen3-tts-tokenizer-iq4_xs.gguf

235 MB
xet

tokenizer file, mixed fp16, fp32 with iq4xs due to block size limit. about 2 months ago