Model comparison
MARTHA-2B-Qwen3.5-Omni vs Qwen3-VL-4B-Instruct
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| MARTHA-2B-Qwen3.5-Omni | Qwen3-VL-4B-Instruct | |
|---|---|---|
| Parameters | 1.9B | 4.4B |
| Architecture | qwen35 | qwen3vl |
| Layers | — | 36 |
| Native context | — | 262,144 |
| Mixture of experts | no | no |
| Quantizations published | 24 | 26 |
| Smallest quantization | 0.67 GiB | 1.01 GiB |
| Q4_K_M | — | 2.33 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | MARTHA-2B-Qwen3.5-Omni | Qwen3-VL-4B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | — | 0.56 GiB | — |
| 8,192 | — | 1.13 GiB | — |
| 16,384 | — | 2.25 GiB | — |
| 32,768 | — | 4.50 GiB | — |
| 65,536 | — | 9.00 GiB | — |
| 131,072 | — | 18.00 GiB | — |