Model comparison
HyperCLOVAX-SEED-Text-Instruct-0.5B vs Llama-3.2-3B-Instruct
At Q4_K_M, HyperCLOVAX-SEED-Text-Instruct-0.5B is the smaller download — 431,882,784 bytes against 2,019,377,440. At long context the gap widens: HyperCLOVAX-SEED-Text-Instruct-0.5B's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| HyperCLOVAX-SEED-Text-Instruct-0.5B | Llama-3.2-3B-Instruct | |
|---|---|---|
| Parameters | 566M | 3.2B |
| Architecture | llama | llama |
| Layers | 24 | 28 |
| Native context | 8,192 | 131,072 |
| Mixture of experts | no | no |
| Quantizations published | 4 | 39 |
| Smallest quantization | 0.39 GiB | 0.85 GiB |
| Q4_K_M | 0.40 GiB | 1.88 GiB |
| Licence | other | — |
KV cache by context
the term that decides long-context viability
| Context | HyperCLOVAX-SEED-Text-Instruct-0.5B | Llama-3.2-3B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | 0.38 GiB | 0.44 GiB | 1.17× |
| 8,192 | 0.75 GiB | 0.88 GiB | 1.17× |
| 16,384 | 1.50 GiB | 1.75 GiB | 1.17× |
| 32,768 | 3.00 GiB | 3.50 GiB | 1.17× |
| 65,536 | 6.00 GiB | 7.00 GiB | 1.17× |
| 131,072 | 12.00 GiB | 14.00 GiB | 1.17× |