Model comparison
next-1b vs HyperCLOVAX-SEED-Text-Instruct-1.5B
At Q4_K_M, next-1b is the smaller download — 806,057,664 bytes against 1,133,974,368.
From the file· summed bytes, KV per layer
Side by side
| next-1b | HyperCLOVAX-SEED-Text-Instruct-1.5B | |
|---|---|---|
| Parameters | 1000M | 1.6B |
| Architecture | gemma3 | llama |
| Layers | 26 | — |
| Native context | 32,768 | — |
| Mixture of experts | no | no |
| Quantizations published | 1 | 1 |
| Smallest quantization | 0.75 GiB | 1.06 GiB |
| Q4_K_M | 0.75 GiB | 1.06 GiB |
| Licence | mit | other |
KV cache by context
the term that decides long-context viability
| Context | next-1b | HyperCLOVAX-SEED-Text-Instruct-1.5B | Ratio |
|---|---|---|---|
| 4,096 | 0.04 GiB | — | — |
| 8,192 | 0.05 GiB | — | — |
| 16,384 | 0.08 GiB | — | — |
| 32,768 | 0.15 GiB | — | — |
| 65,536 | 0.27 GiB | — | — |
| 131,072 | 0.52 GiB | — | — |