Model comparison
gemma-3-4b-it-qat-q4_0-unquantized vs Qwen3-VL-2B-Instruct
At Q4_K_M, Qwen3-VL-2B-Instruct is the smaller download — 1,107,409,952 bytes against 2,489,894,016.
From the file· summed bytes, KV per layer
Side by side
| gemma-3-4b-it-qat-q4_0-unquantized | Qwen3-VL-2B-Instruct | |
|---|---|---|
| Parameters | 4.3B | 2.1B |
| Architecture | gemma3 | qwen3vl |
| Layers | — | 28 |
| Native context | — | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 43 | 46 |
| Smallest quantization | 1.10 GiB | 0.50 GiB |
| Q4_K_M | 2.32 GiB | 1.03 GiB |
| Licence | gemma | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | gemma-3-4b-it-qat-q4_0-unquantized | Qwen3-VL-2B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | — | 0.44 GiB | — |
| 8,192 | — | 0.88 GiB | — |
| 16,384 | — | 1.75 GiB | — |
| 32,768 | — | 3.50 GiB | — |
| 65,536 | — | 7.00 GiB | — |
| 131,072 | — | 14.00 GiB | — |