Compare
Compare models side by side
Choose up to 4 models to see their file size, memory, license and third-party evaluations side by side.
Comparison table
| Item | Kimi-K2.6 moonshotai ✕ Remove |
|---|---|
| Parameters | 1,026.4B |
| Architecture | deepseek2 |
| Max context length | 262,144 |
| Representative quantization and size Measured | UD-Q2_K_XL · 340 GB |
| Memory at 8K Estimated | 342 GB |
| Memory at 32K Estimated | 344 GB |
| VRAM it fits (8K) Estimated | - |
| Smallest quantization (8K) Estimated | UD-Q2_K_XL · 340 GB → 342 GB |
| License | Modified MIT License (Moonshot AI's Kimi) Conditional |
| llama.cpp support | Supported before llama.cpp b4409 |
| Downloads (30 days, total) | 36,528 |
| Human preference (LMArena) | 1,461 Kimi K2.6 |
| Capabilities (Epoch AI) | 151.5 Kimi K2.6 |
| Hard science (GPQA) | 90.8% kimi-k2.6 |
- The representative quantization is Q4_K_M (or the smallest one if missing) from the source with the most downloads. Memory is estimated with an f16 KV cache.
- Third-party evaluations are other organizations' values for the original model before quantization, not this site's rating (sources are on the ranking page).
- This site does not judge which model is better or give an overall score.