Model comparison
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 vs GLM-5.2
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | GLM-5.2 | |
|---|---|---|
| Parameters | 561B | 753B |
| Architecture | nemotron_h_moe | glm-dsa |
| Layers | — | 78 |
| Native context | 262,144 | 1,048,576 |
| Mixture of experts | yes, 512 experts | yes, 256 experts |
| Quantizations published | 15 | 20 |
| Smallest quantization | 175.12 GiB | 169.33 GiB |
| Q4_K_M | — | — |
| Licence | other | mit |
KV cache by context
the term that decides long-context viability
| Context | NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | GLM-5.2 | Ratio |
|---|---|---|---|
| 4,096 | — | 0.34 GiB | — |
| 8,192 | — | 0.69 GiB | — |
| 16,384 | — | 1.37 GiB | — |
| 32,768 | — | 2.74 GiB | — |
| 65,536 | — | 5.48 GiB | — |
| 131,072 | — | 10.97 GiB | — |