Model comparison

solar-pro-preview-instruct vs Qwen-AgentWorld-35B-A3B

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

From the file· summed bytes, KV per layer

Side by side

solar-pro-preview-instructQwen-AgentWorld-35B-A3B
Parameters22.1B34.7B
Architecturellamaqwen35moe
Layers6440
Native context4,096262,144
Mixture of expertsnoyes, 256 experts
Quantizations published1515
Smallest quantization4.46 GiB10.71 GiB
Q4_K_M12.40 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextsolar-pro-preview-instructQwen-AgentWorld-35B-A3BRatio
4,0960.08 GiB
8,1920.16 GiB
16,3840.31 GiB
32,7680.63 GiB
65,5361.25 GiB
131,0722.50 GiB
solar-pro-preview-instruct vs Qwen-AgentWorld-35B-A3B — size, memory and hardware fit — ossmodeldb