Jahaz
/

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

Model card Files Files and versions

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

3.51 GB

Ctrl+K

Ctrl+K

1 contributor

History: 24 commits

Jahaz's picture

MXFP4 wavtokenizer

b110296 verified about 2 months ago

.gitattributes
2.04 kB
MXFP4 wavtokenizer about 2 months ago
Qwen3-tts-0.6b-q8_0..gguf
986 MB
xet

requantized qwen3-tts-0.6b-q8_0.gguf 2 months ago
README.md
694 Bytes
Update README.md about 2 months ago
qwen3-tts-0.6b-MXFP4.gguf
505 MB
xet

update mxfp4 for faster speed about 2 months ago
qwen3-tts-0.6b-iq4_xs.gguf
505 MB
xet

qwen3-tts-o.6b-Iq4xs.gguf 2 months ago
qwen3-tts-0.6b-q5k.gguf
663 MB
xet

better quality than iq4xs in long transcript about 2 months ago
qwen3-tts-tokenizer-MXFP4.gguf
198 MB
xet

MXFP4 wavtokenizer about 2 months ago
qwen3-tts-tokenizer-iq3s.gguf
203 MB
xet

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

Smaller tokenizer 2 months ago
qwen3-tts-tokenizer-iq4_xs.gguf
235 MB
xet

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