Model comparison
Nanbeige4.2-3B vs Qwen3-VL-8B-Instruct-abliterated-v1
At Q4_K_M, Nanbeige4.2-3B is the smaller download — 2,574,807,904 bytes against 5,027,785,792.
From the file· summed bytes, KV per layer
Side by side
| Nanbeige4.2-3B | Qwen3-VL-8B-Instruct-abliterated-v1 | |
|---|---|---|
| Parameters | 4.2B | 8.8B |
| Architecture | nanbeige | qwen3vl |
| Layers | 22 | — |
| Native context | 262,144 | — |
| Mixture of experts | no | no |
| Quantizations published | 22 | 48 |
| Smallest quantization | 1.64 GiB | 1.97 GiB |
| Q4_K_M | 2.40 GiB | 4.68 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Nanbeige4.2-3B | Qwen3-VL-8B-Instruct-abliterated-v1 | Ratio |
|---|---|---|---|
| 4,096 | 0.34 GiB | — | — |
| 8,192 | 0.69 GiB | — | — |
| 16,384 | 1.38 GiB | — | — |
| 32,768 | 2.75 GiB | — | — |
| 65,536 | 5.50 GiB | — | — |
| 131,072 | 11.00 GiB | — | — |