Qwen/Qwen3-Omni-30B-A3B-Instruct
31 derivatives checked
- ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF: Not comparable yet
- marksverdhei/Qwen3-Omni-30B-A3B-FP8: Quantization
- cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit: Quantization
- cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-8bit: Quantization
- YihongJin/Qwen3-Omni-30B-A3B-Instruct-NVFP4-W4A4-full-thinker-awqclip: Quantization
- YihongJin/Qwen3-Omni-30B-A3B-Instruct-NVFP4-W4A16-awq: Quantization
- Intel/Qwen3-Omni-30B-A3B-Instruct-int4-AutoRound: Quantization
- Atotti/Qwen3-Omni-AudioTransformer: Same weights, repacked
- TrevorJS/Qwen3-Omni-30B-A3B-GGUF: Not comparable yet
- cudabenchmarktest/Ornith-1.5-9B-Omni-GGUF: Not comparable yet
- shunyang90/Qwen3-Omni-30B-A3B-Instruct-NVFP4: Quantization
- YihongJin/Qwen3-Omni-30B-A3B-Instruct-NVFP4-W4A4-experts-mse: Quantization
- cudabenchmarktest/Qwen3.8-27B-E03-Obliterated-Omni-Audio-Bridge-GGUF: Not comparable yet
- cudabenchmarktest/Qwen3.8-27B-E03-Obliterated-Omni-GGUF: Not comparable yet
- pherber3/Qwen3-Omni-30B-A3B-Instruct-4bit-mlx: Quantization
- ZolMik2004/Qwen3-Omni-30B-A3B-Instruct-HybridQuant-MLX: Quantization
- cudabenchmarktest/Ornith-1.5-9B-Omni-Audio-Bridge-GGUF: Not comparable yet
- VikramPal/Qwen3-Omni-30B-A3B-Thinker-QLoRA: Adapter
- steampunque/Qwen3-Omni-30B-A3B-Instruct-MP-GGUF: Not comparable yet
- DeepMentor/qwen3-omni-30B-a3b-instruct-gguf: Not comparable yet
- NandemoGHS/Anime-Speech-Japanese-Refiner: LoRA-style
- 88plug/Qwen3-Omni-30B-W4A16: Quantization
- Cloudflare/clef-omni: LoRA-style
- YihongJin/Qwen3-Omni-30B-A3B-Instruct-NVFP4-W4A16-max: Quantization
- PleasedPenguin/A2R-30B-A3B: LoRA-style
- ASLP-lab/FM-Speech: Partial fine-tune
- deepcrayon/AniMUL-v1: Partial fine-tune
- beyoru/Omni-PLAnh-exp: LoRA-style
- Tung111/OPOD-Qwen3-Omni-30B-A3B: Partial fine-tune
- CMKL/MANGO-Qwen3-Omni-30B-A3B-Instruct: LoRA-style
16 other repos hold byte-for-byte identical weight files.