Model comparison
Phi-4-reasoning-plus vs Qwen3-Coder-30B-A3B-Instruct
At Q4_K_M, Phi-4-reasoning-plus is the smaller download — 9,053,116,128 bytes against 18,556,689,568. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 2.1× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Phi-4-reasoning-plus | Qwen3-Coder-30B-A3B-Instruct | |
|---|---|---|
| Parameters | 14.7B | 30.5B |
| Architecture | phi3 | qwen3moe |
| Layers | 40 | 48 |
| Native context | 32,768 | 262,144 |
| Mixture of experts | no | yes, 128 experts |
| Quantizations published | 46 | 46 |
| Smallest quantization | 3.33 GiB | 7.46 GiB |
| Q4_K_M | 8.43 GiB | 17.28 GiB |
| Licence | mit | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Phi-4-reasoning-plus | Qwen3-Coder-30B-A3B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | 0.78 GiB | 0.38 GiB | 2.08× |
| 8,192 | 1.56 GiB | 0.75 GiB | 2.08× |
| 16,384 | 3.13 GiB | 1.50 GiB | 2.08× |
| 32,768 | 6.25 GiB | 3.00 GiB | 2.08× |
| 65,536 | 12.50 GiB | 6.00 GiB | 2.08× |
| 131,072 | 25.00 GiB | 12.00 GiB | 2.08× |