Model comparison

OpenELM-3B-Instruct vs Qwen3-VL-8B-Instruct-abliterated-v1

At Q4_K_M, OpenELM-3B-Instruct is the smaller download — 1,887,788,096 bytes against 5,027,785,792.

From the file· summed bytes, KV per layer

Side by side

OpenELM-3B-InstructQwen3-VL-8B-Instruct-abliterated-v1
Parameters3.0B8.8B
Architectureopenelmqwen3vl
Layers
Native context
Mixture of expertsnono
Quantizations published1548
Smallest quantization1.07 GiB1.97 GiB
Q4_K_M1.76 GiB4.68 GiB
Licenceapple-amlrapache-2.0

KV cache by context

the term that decides long-context viability
ContextOpenELM-3B-InstructQwen3-VL-8B-Instruct-abliterated-v1Ratio
4,096
8,192
16,384
32,768
65,536
131,072