Model comparison
HyperCLOVAX-SEED-Text-Instruct-1.5B vs Qwen2.5-7B-Instruct
At Q4_K_M, HyperCLOVAX-SEED-Text-Instruct-1.5B is the smaller download — 1,133,974,368 bytes against 4,683,073,632.
From the file· summed bytes, KV per layer
Side by side
| HyperCLOVAX-SEED-Text-Instruct-1.5B | Qwen2.5-7B-Instruct | |
|---|---|---|
| Parameters | 1.6B | 7.6B |
| Architecture | llama | qwen2 |
| Layers | — | 28 |
| Native context | — | 32,768 |
| Mixture of experts | no | no |
| Quantizations published | 1 | 32 |
| Smallest quantization | 1.06 GiB | 2.59 GiB |
| Q4_K_M | 1.06 GiB | 4.36 GiB |
| Licence | other | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | HyperCLOVAX-SEED-Text-Instruct-1.5B | Qwen2.5-7B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | — | 0.22 GiB | — |
| 8,192 | — | 0.44 GiB | — |
| 16,384 | — | 0.88 GiB | — |
| 32,768 | — | 1.75 GiB | — |
| 65,536 | — | 3.50 GiB | — |
| 131,072 | — | 7.00 GiB | — |