Model comparison
Trinity-Nano-Preview vs HyperCLOVAX-SEED-Text-Instruct-1.5B
At Q4_K_M, HyperCLOVAX-SEED-Text-Instruct-1.5B is the smaller download — 1,133,974,368 bytes against 3,786,957,088.
From the file· summed bytes, KV per layer
Side by side
| Trinity-Nano-Preview | HyperCLOVAX-SEED-Text-Instruct-1.5B | |
|---|---|---|
| Parameters | 6.1B | 1.6B |
| Architecture | afmoe | llama |
| Layers | 56 | — |
| Native context | 131,072 | — |
| Mixture of experts | yes, 128 experts | no |
| Quantizations published | 50 | 1 |
| Smallest quantization | 1.94 GiB | 1.06 GiB |
| Q4_K_M | 3.53 GiB | 1.06 GiB |
| Licence | apache-2.0 | other |
KV cache by context
the term that decides long-context viability
| Context | Trinity-Nano-Preview | HyperCLOVAX-SEED-Text-Instruct-1.5B | Ratio |
|---|---|---|---|
| 4,096 | 0.16 GiB | — | — |
| 8,192 | 0.21 GiB | — | — |
| 16,384 | 0.32 GiB | — | — |
| 32,768 | 0.54 GiB | — | — |
| 65,536 | 0.98 GiB | — | — |
| 131,072 | 1.85 GiB | — | — |