Very Large GGUFs
Collection
GGUF quantized versions of very large models - over 100B parameters
•
52 items
•
Updated
•
5
'Make knowledge free for everyone'
Original INT4 model has been dequantized with my own custom script:
DQ_int4-to-bf16_dequant (inspired by the deepseek V3 dequant script)
Test/Proof
Zero Short Hexa-ball test, generated code by the Q3 quant produced:
Quantized version of: moonshotai/Kimi-K2-Thinking
- Downloads last month
- 1,771
Hardware compatibility
Log In
to view the estimation
2-bit
3-bit
4-bit
Model tree for DevQuasar/moonshotai.Kimi-K2-Thinking-GGUF
Base model
moonshotai/Kimi-K2-Thinking