Model comparison
LFM2.5-VL-1.6B vs MiniCPM-V-4.6
At Q4_K_M, MiniCPM-V-4.6 is the smaller download — 529,101,504 bytes against 730,895,968.
From the file· summed bytes, KV per layer
Side by side
| LFM2.5-VL-1.6B | MiniCPM-V-4.6 | |
|---|---|---|
| Parameters | 1.6B | 1.3B |
| Architecture | lfm2 | qwen35 |
| Layers | 16 | 24 |
| Native context | 128,000 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 23 | 15 |
| Smallest quantization | 0.45 GiB | 0.47 GiB |
| Q4_K_M | 0.68 GiB | 0.49 GiB |
| Licence | other | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | LFM2.5-VL-1.6B | MiniCPM-V-4.6 | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | 0.05 GiB | 1.00× |
| 8,192 | 0.09 GiB | 0.09 GiB | 1.00× |
| 16,384 | 0.19 GiB | 0.19 GiB | 1.00× |
| 32,768 | 0.38 GiB | 0.38 GiB | 1.00× |
| 65,536 | 0.75 GiB | 0.75 GiB | 1.00× |
| 131,072 | 1.50 GiB | 1.50 GiB | 1.00× |