Model comparison

Phi-3.5-mini-instruct vs Qwen3-VL-8B-Instruct-abliterated-v1

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

Phi-3.5-mini-instructQwen3-VL-8B-Instruct-abliterated-v1
Parameters3.8B8.8B
Architecturellamaqwen3vl
Layers32
Native context131,072
Mixture of expertsnono
Quantizations published2448
Smallest quantization0.82 GiB1.97 GiB
Q4_K_M4.68 GiB
Licencemitapache-2.0

KV cache by context

the term that decides long-context viability
ContextPhi-3.5-mini-instructQwen3-VL-8B-Instruct-abliterated-v1Ratio
4,0961.50 GiB
8,1923.00 GiB
16,3846.00 GiB
32,76812.00 GiB
65,53624.00 GiB
131,07248.00 GiB