Model comparison
MiniCPM-V-4 vs Qwen3.5-9B
At Q4_K_M, MiniCPM-V-4 is the smaller download — 2,189,861,216 bytes against 5,627,044,256.
From the file· summed bytes, KV per layer
Side by side
| MiniCPM-V-4 | Qwen3.5-9B | |
|---|---|---|
| Parameters | 4.1B | 9.7B |
| Architecture | llama | qwen35 |
| Layers | 32 | 32 |
| Native context | 32,768 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 10 | 34 |
| Smallest quantization | 1.94 GiB | 2.97 GiB |
| Q4_K_M | 2.04 GiB | 5.24 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | MiniCPM-V-4 | Qwen3.5-9B | Ratio |
|---|---|---|---|
| 4,096 | 0.13 GiB | 0.13 GiB | 1.00× |
| 8,192 | 0.25 GiB | 0.25 GiB | 1.00× |
| 16,384 | 0.50 GiB | 0.50 GiB | 1.00× |
| 32,768 | 1.00 GiB | 1.00 GiB | 1.00× |
| 65,536 | 2.00 GiB | 2.00 GiB | 1.00× |
| 131,072 | 4.00 GiB | 4.00 GiB | 1.00× |