moonshotai/Kimi-K2.5
27 derivatives checked
- nvidia/Kimi-K2.5-NVFP4: Different architecture
- mlx-community/Kimi-K2.5: Same weights, repacked
- amd/Kimi-K2.5-MXFP4: Partial fine-tune
- unsloth/Kimi-K2.5-GGUF: Quantization
- nikita-savelyev-cerebras/tiny-random-kimi-k2.5: Quantization
- bartowski/moonshotai_Kimi-K2.5-GGUF: Quantization
- eatang/Kimi-K2.5-2layer: Same weights, repacked (fewer layers)
- lightseekorg/kimi-k2.5-eagle3-mla: Quantization
- lightseekorg/kimi-k2.5-eagle3: Quantization
- eatang/Kimi-K2.5-2layer-BF16: Quantization
- QuantPasture/Kimi-K2.5-GGUF: Quantization
- ISTA-DASLab/Kimi-K2.5-2Bit-GSQ: Different architecture
- ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ: Different architecture
- nvidia/Kimi-K2.5-Thinking-Eagle3: Quantization
- mlx-community/Kimi-K2.5-3bit: Different architecture
- mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8: Different architecture
- spicyneuron/Kimi-K2.5-MLX-2.8bit: Different architecture
- biosai-hf/kimi-k2.5-eagle3-mla: Quantization
- DevQuasar/moonshotai.Kimi-K2.5-GGUF: Quantization
- spicyneuron/Kimi-K2.5-MLX-2.5bit: Different architecture
- promotewillgo/apollo5GWKiiudZ5AePoLA6HxH9HwF3p8Q98o1Q6tRKepsp4EouRak: Same weights, repacked
- Drifter4242/Kimi-K2.5-vision: Quantization
- unsloth/Kimi-K2.5: Identical copy
- amd/Kimi-K2.5-W4A8: Different architecture
- yujiepan/kimi-k2.5-tiny-random: Quantization
- AxionML/Kimi-K2.5-MXFP8: Partial fine-tune
- Ex0bit/Kimi-K2.5-PRISM-REAP-530B-A32B: Partial fine-tune (fewer layers)