Model comparison

Qwen3-VL-8B-Instruct-abliterated-v2 vs Qwen3.5-9B

At Q4_K_M, Qwen3-VL-8B-Instruct-abliterated-v2 is the smaller download — 5,027,785,824 bytes against 5,627,044,256.

From the file· summed bytes, KV per layer

Side by side

Qwen3-VL-8B-Instruct-abliterated-v2Qwen3.5-9B
Parameters8.8B9.7B
Architectureqwen3vlqwen35
Layers32
Native context262,144
Mixture of expertsnono
Quantizations published3634
Smallest quantization3.06 GiB2.97 GiB
Q4_K_M4.68 GiB5.24 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-VL-8B-Instruct-abliterated-v2Qwen3.5-9BRatio
4,0960.13 GiB
8,1920.25 GiB
16,3840.50 GiB
32,7681.00 GiB
65,5362.00 GiB
131,0724.00 GiB