Model comparison
Bielik-11B-v2.3-Instruct vs gemma-4-E4B-it
At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 6,724,050,496. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 12.4× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Bielik-11B-v2.3-Instruct | gemma-4-E4B-it | |
|---|---|---|
| Parameters | 11.2B | 8.0B |
| Architecture | llama | gemma4 |
| Layers | 50 | 42 |
| Native context | 32,768 | 131,072 |
| Mixture of experts | no | no |
| Quantizations published | 4 | 36 |
| Smallest quantization | 6.26 GiB | 3.30 GiB |
| Q4_K_M | 6.26 GiB | 4.64 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Bielik-11B-v2.3-Instruct | gemma-4-E4B-it | Ratio |
|---|---|---|---|
| 4,096 | 0.78 GiB | 0.12 GiB | 6.35× |
| 8,192 | 1.56 GiB | 0.18 GiB | 8.79× |
| 16,384 | 3.13 GiB | 0.29 GiB | 10.88× |
| 32,768 | 6.25 GiB | 0.51 GiB | 12.36× |
| 65,536 | 12.50 GiB | 0.94 GiB | 13.25× |
| 131,072 | 25.00 GiB | 1.82 GiB | 13.75× |