Model comparison
Qwen3.5-9B vs glm-4v-9b
At Q4_K_M, Qwen3.5-9B is the smaller download — 5,627,044,256 bytes against 6,166,574,560.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.5-9B | glm-4v-9b | |
|---|---|---|
| Parameters | 9.7B | 13.9B |
| Architecture | qwen35 | glm4 |
| Layers | 32 | — |
| Native context | 262,144 | — |
| Mixture of experts | no | no |
| Quantizations published | 34 | 14 |
| Smallest quantization | 2.97 GiB | 3.73 GiB |
| Q4_K_M | 5.24 GiB | 5.74 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.5-9B | glm-4v-9b | Ratio |
|---|---|---|---|
| 4,096 | 0.13 GiB | — | — |
| 8,192 | 0.25 GiB | — | — |
| 16,384 | 0.50 GiB | — | — |
| 32,768 | 1.00 GiB | — | — |
| 65,536 | 2.00 GiB | — | — |
| 131,072 | 4.00 GiB | — | — |