Model comparison
Qwen3-16B-A3B vs Qwen3-30B-A3B-Thinking-2507
At Q4_K_M, Qwen3-16B-A3B is the smaller download — 9,754,940,096 bytes against 18,556,685,824.
From the file· summed bytes, KV per layer
Side by side
| Qwen3-16B-A3B | Qwen3-30B-A3B-Thinking-2507 | |
|---|---|---|
| Parameters | 16.0B | 30.5B |
| Architecture | qwen3moe | qwen3moe |
| Layers | 48 | 48 |
| Native context | 40,960 | 262,144 |
| Mixture of experts | yes, 64 experts | yes, 128 experts |
| Quantizations published | 46 | 51 |
| Smallest quantization | 4.12 GiB | 7.05 GiB |
| Q4_K_M | 9.08 GiB | 17.28 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3-16B-A3B | Qwen3-30B-A3B-Thinking-2507 | Ratio |
|---|---|---|---|
| 4,096 | 0.38 GiB | 0.38 GiB | 1.00× |
| 8,192 | 0.75 GiB | 0.75 GiB | 1.00× |
| 16,384 | 1.50 GiB | 1.50 GiB | 1.00× |
| 32,768 | 3.00 GiB | 3.00 GiB | 1.00× |
| 65,536 | 6.00 GiB | 6.00 GiB | 1.00× |
| 131,072 | 12.00 GiB | 12.00 GiB | 1.00× |