Model comparison

MARTHA-2B-Qwen3.5-Omni vs Qwen3-VL-2B-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-OmniQwen3-VL-2B-Instruct
Parameters1.9B2.1B
Architectureqwen35qwen3vl
Layers28
Native context262,144
Mixture of expertsnono
Quantizations published2446
Smallest quantization0.67 GiB0.50 GiB
Q4_K_M1.03 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextMARTHA-2B-Qwen3.5-OmniQwen3-VL-2B-InstructRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB