Model comparison
llava-llama-3-8b-v1_1-transformers vs Qwen3.5-4B
At Q4_K_M, Qwen3.5-4B is the smaller download — 2,707,513,696 bytes against 4,921,098,752.
From the file· summed bytes, KV per layer
Side by side
| llava-llama-3-8b-v1_1-transformers | Qwen3.5-4B | |
|---|---|---|
| Parameters | 8.4B | 4.7B |
| Architecture | llama | qwen35 |
| Layers | — | 32 |
| Native context | 8,192 | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 15 | 57 |
| Smallest quantization | 3.41 GiB | 1.42 GiB |
| Q4_K_M | 4.58 GiB | 2.52 GiB |
| Licence | — | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | llava-llama-3-8b-v1_1-transformers | Qwen3.5-4B | 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 | — |