Model comparison
Luna-7B-A4B 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 4,126,489,312.
From the file· summed bytes, KV per layer
Side by side
| Luna-7B-A4B | HyperCLOVAX-SEED-Text-Instruct-1.5B | |
|---|---|---|
| Parameters | 6.7B | 1.6B |
| Architecture | qwen3moe | llama |
| Layers | 36 | — |
| Native context | 262,144 | — |
| Mixture of experts | yes, 2 experts | no |
| Quantizations published | 36 | 1 |
| Smallest quantization | 1.49 GiB | 1.06 GiB |
| Q4_K_M | 3.84 GiB | 1.06 GiB |
| Licence | mit | other |
KV cache by context
the term that decides long-context viability
| Context | Luna-7B-A4B | HyperCLOVAX-SEED-Text-Instruct-1.5B | Ratio |
|---|---|---|---|
| 4,096 | 0.56 GiB | — | — |
| 8,192 | 1.13 GiB | — | — |
| 16,384 | 2.25 GiB | — | — |
| 32,768 | 4.50 GiB | — | — |
| 65,536 | 9.00 GiB | — | — |
| 131,072 | 18.00 GiB | — | — |