moonshotai/Kimi-K2.6
27 derivatives checked
- lightseekorg/kimi-k2.6-eagle3-mla: Quantization
- unsloth/Kimi-K2.6-GGUF: Quantization
- nvidia/Kimi-K2.6-NVFP4: Different architecture
- amd/Kimi-K2.6-MXFP4: Partial fine-tune
- RedHatAI/Kimi-K2.6-FP8-BLOCK: Different architecture
- bartowski/moonshotai_Kimi-K2.6-GGUF: Quantization
- mlx-community/Kimi-K2.6-mlx-DQ3_K_M-q8: Different architecture
- nvidia/Kimi-K2.6-Eagle3: Quantization
- DevQuasar/moonshotai.Kimi-K2.6-GGUF: Quantization
- AesSedai/Kimi-K2.6-GGUF: Quantization
- aidiffuser/Kimi-K2.6-MLX-4bit: Same weights, repacked
- nvidia/Kimi-K2.6-DFlash: Quantization
- spicyneuron/Kimi-K2.6-MLX-3.6bit: Different architecture
- spicyneuron/Kimi-K2.6-MLX-3.3bit: Different architecture
- ISTA-DASLab/Kimi-K2.6-2Bit-GSQ: Different architecture
- novita/kimi-k2.6-dspark: Quantization
- gghfez/Kimi-K2.6-control-vectors: Quantization
- RedHatAI/Kimi-K2.6-NVFP4: Different architecture
- webbrain-one/DeepSeek-V4-Flash-Vision-NVFP4: Different architecture
- tiny-random/kimi-k2.6: Quantization
- unsloth/Kimi-K2.6: Identical copy
- baa-ai/Kimi-K2.6-RAM-GGUF: Quantization
- Youssofal/Kimi-K2.6-GGUF: Quantization
- freakyskittle/kimi-k2.75-code: Full fine-tune (fewer layers)
- freakyskittle/Kimi-K2.6-DFlash-baseinit: Quantization
- amd/Kimi-K2.6-NVFP4: Different architecture
- webbrain-one/Laguna-XS-2.1-Vision-NVFP4: Different architecture