Qwen/Qwen3-Next-80B-A3B-Thinking
32 derivatives checked
- unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF: Same weights, converted
- bartowski/Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF: Quantization
- Qwen/Qwen3-Next-80B-A3B-Thinking-FP8: Quantization
- nvidia/Qwen3-Next-80B-A3B-Thinking-NVFP4: Quantization
- mradermacher/Qwen3-Next-80B-A3B-Thinking-i1-GGUF: Quantization
- lmstudio-community/Qwen3-Next-80B-A3B-Thinking-GGUF: Quantization
- mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit: Quantization
- cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit: Quantization
- mlx-community/Qwen3-Next-80B-A3B-Thinking-8bit: Quantization
- a4lg/Qwen3-Next-80B-A3B-Thinking-MTP-ONLY-GGUF: Not comparable yet
- John1604/Qwen3-Next-80B-A3B-Thinking-gguf: Quantization
- minjaechoi/qwen3next-80b-a3b-2p12bit-r26: LoRA-style
- lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-4bit: Quantization
- minjaechoi/qwen3next-80b-a3b-2p02bit-r22: LoRA-style
- INC4AI/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound: Quantization
- minjaechoi/qwen3next-80b-a3b-2p25bit-r24: LoRA-style
- lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-8bit: Quantization
- minjaechoi/qwen3next-80b-a3b-2p36bit-r23: LoRA-style
- lefromage/Qwen3-Next-80B-A3B-Thinking-GGUF: Quantization
- lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-6bit: Quantization
- MultiverseComputingCAI/Qwen3-Next-80B-A3B-Thinking-Uncensored: Partial fine-tune
- lovedheart/Qwen3-Next-REAP-25B-A3B-Thinking-GGUF: Same weights, converted
- minjaechoi/qwen3next-80b-a3b-2p02bit-r32_v7: LoRA-style
- lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-5bit: Quantization
- mradermacher/Qwen3-Next-80B-A3B-Thinking-GGUF: Quantization
- lovedheart/Qwen3-Next-REAP-20B-A3B-Thinking-GGUF: Same weights, converted
- nightmedia/Qwen3-Next-80B-A3B-Thinking-qx53n-mlx: Quantization
- RESMP-DEV/Qwen3-Next-80B-A3B-Thinking-NVFP4: Quantization
- RedHatAI/Qwen3-Next-80B-A3B-Thinking-NVFP4: Quantization
- bgg1996/Melinoe-Next-80B-A3B-Thinking-v0: Partial fine-tune
6 other repos hold byte-for-byte identical weight files.