Model comparison
Qwen3.8-27B vs Ling-lite
At Q4_K_M, Ling-lite is the smaller download — 11,175,490,944 bytes against 16,810,714,336.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.8-27B | Ling-lite | |
|---|---|---|
| Parameters | 27.8B | 16.8B |
| Architecture | qwen35 | bailingmoe |
| Layers | 64 | 28 |
| Native context | 262,144 | 32,768 |
| Mixture of experts | no | yes, 64 experts |
| Quantizations published | 22 | 54 |
| Smallest quantization | 8.39 GiB | 5.97 GiB |
| Q4_K_M | 15.66 GiB | 10.41 GiB |
| Licence | apache-2.0 | mit |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.8-27B | Ling-lite | Ratio |
|---|---|---|---|
| 4,096 | 0.25 GiB | 0.22 GiB | 1.14× |
| 8,192 | 0.50 GiB | 0.44 GiB | 1.14× |
| 16,384 | 1.00 GiB | 0.88 GiB | 1.14× |
| 32,768 | 2.00 GiB | 1.75 GiB | 1.14× |
| 65,536 | 4.00 GiB | 3.50 GiB | 1.14× |
| 131,072 | 8.00 GiB | 7.00 GiB | 1.14× |