Model comparison
Qwen3-Coder-30B-A3B-Instruct vs gemma-4-E2B-it-qat-q4_0-unquantized
These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-E2B-it-qat-q4_0-unquantized's KV cache at 32K is 12.2× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Qwen3-Coder-30B-A3B-Instruct | gemma-4-E2B-it-qat-q4_0-unquantized | |
|---|---|---|
| Parameters | 30.5B | 5.1B |
| Architecture | qwen3moe | gemma4 |
| Layers | 48 | 35 |
| Native context | 262,144 | 131,072 |
| Mixture of experts | yes, 128 experts | no |
| Quantizations published | 46 | 3 |
| Smallest quantization | 7.46 GiB | 3.12 GiB |
| Q4_K_M | 17.28 GiB | — |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3-Coder-30B-A3B-Instruct | gemma-4-E2B-it-qat-q4_0-unquantized | Ratio |
|---|---|---|---|
| 4,096 | 0.38 GiB | 0.05 GiB | 6.86× |
| 8,192 | 0.75 GiB | 0.08 GiB | 9.14× |
| 16,384 | 1.50 GiB | 0.14 GiB | 10.97× |
| 32,768 | 3.00 GiB | 0.25 GiB | 12.19× |
| 65,536 | 6.00 GiB | 0.46 GiB | 12.91× |
| 131,072 | 12.00 GiB | 0.90 GiB | 13.30× |