Model comparison
gliner2-base-v1 vs Qwen2.5-0.5B-Instruct
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| gliner2-base-v1 | Qwen2.5-0.5B-Instruct | |
|---|---|---|
| Parameters | 208M | 494M |
| Architecture | deberta | qwen2 |
| Layers | — | 24 |
| Native context | — | 32,768 |
| Mixture of experts | no | no |
| Quantizations published | 1 | 32 |
| Smallest quantization | 0.13 GiB | 0.31 GiB |
| Q4_K_M | — | 0.37 GiB |
| Licence | — | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | gliner2-base-v1 | Qwen2.5-0.5B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | — | 0.05 GiB | — |
| 8,192 | — | 0.09 GiB | — |
| 16,384 | — | 0.19 GiB | — |
| 32,768 | — | 0.38 GiB | — |
| 65,536 | — | 0.75 GiB | — |
| 131,072 | — | 1.50 GiB | — |