Model comparison
Gemma-The-Writer-N-Restless-Quill-10B-Uncensored 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 6,100,479,520.
From the file· summed bytes, KV per layer
Side by side
| Gemma-The-Writer-N-Restless-Quill-10B-Uncensored | HyperCLOVAX-SEED-Text-Instruct-1.5B | |
|---|---|---|
| Parameters | 10.0B | 1.6B |
| Architecture | gemma2 | llama |
| Layers | 46 | — |
| Native context | 8,192 | — |
| Mixture of experts | no | no |
| Quantizations published | 31 | 1 |
| Smallest quantization | 2.37 GiB | 1.06 GiB |
| Q4_K_M | 5.68 GiB | 1.06 GiB |
| Licence | apache-2.0 | other |
KV cache by context
the term that decides long-context viability
| Context | Gemma-The-Writer-N-Restless-Quill-10B-Uncensored | HyperCLOVAX-SEED-Text-Instruct-1.5B | Ratio |
|---|---|---|---|
| 4,096 | 1.44 GiB | — | — |
| 8,192 | 2.25 GiB | — | — |
| 16,384 | 3.68 GiB | — | — |
| 32,768 | 6.56 GiB | — | — |
| 65,536 | 12.31 GiB | — | — |
| 131,072 | 23.81 GiB | — | — |