moonshotai/Kimi-K2-Thinking
15 derivatives checked
- nvidia/Kimi-K2-Thinking-NVFP4: Different architecture
- unsloth/Kimi-K2-Thinking-GGUF: Quantization
- bartowski/moonshotai_Kimi-K2-Thinking-GGUF: Quantization
- mlx-community/Kimi-K2-Thinking: Same weights, repacked
- amd/Kimi-K2-Thinking-MXFP4: Partial fine-tune
- DevQuasar/moonshotai.Kimi-K2-Thinking-GGUF: Quantization
- mlx-community/Kimi-K2-Thinking-4bit: Different architecture
- DevQuasar-2/moonshotai.Kimi-K2-Thinking-BF16: Quantization
- unsloth/Kimi-K2-Thinking: Identical copy
- mlx-community/Kimi-K2-Thinking-3bit: Different architecture
- nvidia/Kimi-K2-Thinking-Eagle3: Quantization
- amd/Kimi-K2-Thinking-W4A8: Different architecture
- squ11z1/Hypnos-Colossus-1T: Quantization
- moxin-org/Kimi-K2-Thinking-Moxin-GGUF: Quantization
- amd/Kimi-K2-Thinking-MXFP4-AttnFP8: Partial fine-tune