FreeLLMAll models › Compare
kimi-k2.5-thinking vs nvidia-nemotron-3-ultra-550b-a55b-nvfp4
kimi-k2.5-thinking and nvidia-nemotron-3-ultra-550b-a55b-nvfp4 are about even on Arena (1445 vs 1445): in a blind vote each wins about half the time.
kimi-k2.5-thinking1445Arena chat · #62 of 416
nvidia-nemotron-3-ultra-550b-a55b-nvfp41445Arena chat · #64 of 416
Arena scores by category
| Category | kimi-k2.5-thinking | nvidia-nemotron-3-ultra-550b-a55b-nvfp4 | Ahead |
|---|---|---|---|
| Chat | 1445 | 1445 | about even |
Scores from blind human votes on Arena. A gap under 10 points is too small to call.
Size and where to use them free
| kimi-k2.5-thinking | nvidia-nemotron-3-ultra-550b-a55b-nvfp4 | |
|---|---|---|
| Made by | moonshot | nvidia |
| Size | not public | 560.5 B (55 B active) |
| 4-bit download | — | 341 GB |
| Use it free | Modified MIT license | download and run at home · OpenMDW-1.1 license |
Speed at home
| Hardware | kimi-k2.5-thinking | nvidia-nemotron-3-ultra-550b-a55b-nvfp4 |
|---|---|---|
| RTX 3090 | online only | does not fit |
| RTX 4090 | online only | does not fit |
| RTX 5090 | online only | does not fit |
| RX 7900 XTX | online only | does not fit |
| Mac M4 Max 128 GB | online only | does not fit |
| Ryzen AI Max+ 395 128 GB | online only | does not fit |
Estimates at 4-bit with an 8K context, 64 GB of system RAM for offload, calibrated on 44 real llama.cpp tests.
Try them yourself
Ask both the same question side by side in Try & compare, or vote blind between free models in Free Arena.
More comparisons
- kimi-k2.5-thinking vs MiMo-V2.6-Pro
- kimi-k2.5-thinking vs Kimi K3 (Max)
- kimi-k2.5-thinking vs GLM-5.3 (Max)
- kimi-k2.5-thinking vs GLM-5.3-Flash
- kimi-k2.5-thinking vs GLM-5.2 (Max)
- kimi-k2.5-thinking vs MiMo-V2.5-Pro
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 vs MiMo-V2.6-Pro
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 vs Kimi K3 (Max)
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 vs GLM-5.3 (Max)
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 vs GLM-5.3-Flash