cstr/qwen3-tts-1.7b-base-GGUF
Not comparable yet vs Qwen/Qwen3-TTS-12Hz-1.7B-Base. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (76 of 480/480 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs Qwen/Qwen3-TTS-12Hz-1.7B-Base. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (76 of 480/480 match), usually an architecture llama.cpp's name map doesn't cover yet.