Model comparison
Qwen3.5-9B vs llava-llama-3-8b-v1_1-transformers
At Q4_K_M, llava-llama-3-8b-v1_1-transformers is the smaller download — 4,921,098,752 bytes against 5,627,044,256.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.5-9B | llava-llama-3-8b-v1_1-transformers | |
|---|---|---|
| Parameters | 9.7B | 8.4B |
| Architecture | qwen35 | llama |
| Layers | 32 | — |
| Native context | 262,144 | 8,192 |
| Mixture of experts | no | no |
| Quantizations published | 34 | 15 |
| Smallest quantization | 2.97 GiB | 3.41 GiB |
| Q4_K_M | 5.24 GiB | 4.58 GiB |
| Licence | apache-2.0 | — |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.5-9B | llava-llama-3-8b-v1_1-transformers | 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 | — | — |