Repository: localaiLicense: apache-2.0
MOSS-TTS-Local v1.5 (C++/ggml, moss-tts.cpp), Q8_0 (~6 GB), near-lossless. Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 (a GPT-J local transformer decoded through the MOSS-Audio-Tokenizer-v2 neural codec), 48kHz stereo output with reference-audio voice cloning (set `voice` to a reference .wav). Verified per component against the reference PyTorch and about 2x faster per frame on CPU.
Links
Tags
MOSS-TTS-Local v1.5 (C++/ggml, moss-tts.cpp), F16 (~9.4 GB), code-exact versus the reference. 48kHz stereo text-to-speech with reference-audio voice cloning.
Links
Tags
Repository: localaiLicense: apache-2.0

MOSS-Image-Base is a 5B diffusion transformer image generation model from OpenMOSS-Team. It uses Qwen3.5 9B as the LLM text encoder, the FLUX.2 VAE, and an external tokenizer. The Base variant supports text-to-image generation with classifier-free guidance (default: CFG 3.0, 1024x1024). This entry uses the int8_convrot quantization of the diffusion model (~5.4 GB).
Links
Tags
Repository: localaiLicense: apache-2.0

MOSS-Image-SFT is the supervised fine-tuned variant of MOSS-Image, a 5B diffusion transformer image generation model from OpenMOSS-Team. It uses Qwen3.5 9B as the LLM text encoder, the FLUX.2 VAE, and an external tokenizer. The SFT variant produces higher-quality outputs with classifier-free guidance (default: CFG 3.0, 1024x1024). This entry uses the int8_convrot quantization of the diffusion model (~5.4 GB).
Links
Tags
Repository: localaiLicense: apache-2.0
MOSS-Image is a 5B diffusion transformer text-to-image model that uses the FLUX.2 VAE and a Qwen3.5 9B text encoder. This is the SFT variant. This is the Q4_K quantization of the diffusion model (~3.3 GB) by leejet for stable-diffusion.cpp. The bundle also pulls the Qwen3.5 9B Q4_K_M text encoder (~5.7 GB), the FLUX.2 VAE and the Qwen3.5 tokenizer file, which must be given explicitly because Qwen3.5 does not use the embedded Qwen vocabulary. Use image dimensions divisible by 16.
Links
Tags
Repository: localaiLicense: apache-2.0
MOSS-Transcribe-Diarize 0.9B, an end-to-end audio understanding model for joint multi-speaker transcription, speaker diarization and timestamping in a single pass. Q5_K GGUF for the moss-transcribe-cpp backend (C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize), byte-identical to the reference at ~1/6 the size. Faster than the reference PyTorch runtime on CPU (1.6 to 2.2x).
Links
Tags