Model comparison
Miss_MARTHA-9B-Qwen3.5-Omni 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 5,629,108,544.
From the file· summed bytes, KV per layer
Side by side
| Miss_MARTHA-9B-Qwen3.5-Omni | HyperCLOVAX-SEED-Text-Instruct-1.5B | |
|---|---|---|
| Parameters | 9.0B | 1.6B |
| Architecture | qwen35 | llama |
| Layers | 32 | — |
| Native context | 262,144 | — |
| Mixture of experts | no | no |
| Quantizations published | 53 | 1 |
| Smallest quantization | 2.28 GiB | 1.06 GiB |
| Q4_K_M | 5.24 GiB | 1.06 GiB |
| Licence | — | other |
KV cache by context
the term that decides long-context viability
| Context | Miss_MARTHA-9B-Qwen3.5-Omni | HyperCLOVAX-SEED-Text-Instruct-1.5B | Ratio |
|---|---|---|---|
| 4,096 | 0.13 GiB | — | — |
| 8,192 | 0.25 GiB | — | — |
| 16,384 | 0.50 GiB | — | — |
| 32,768 | 1.00 GiB | — | — |
| 65,536 | 2.00 GiB | — | — |
| 131,072 | 4.00 GiB | — | — |