Skip to content
VRAMwise

gpt-oss-120b (MoE): VRAM by quant

117.0B params · KV field None · max context field 131072.

QuantBitsWeight GB sketch
Q4_K_M4.85 bpw~72.5 GB
Q5_K_M5.7 bpw~84.2 GB
Q6_K6.6 bpw~97.1 GB
Q8_08.5 bpw~125.2 GB
MXFP44.25 bpw~64.4 GB
F16/BF1616.0 bpw~234.0 GB

Add KV for your context length in context VRAM. Overall fit: VRAM fit.

Educational. MoE active params may differ from total params.

Frequently asked questions

Size?

117.0B.

gpt-oss-120b (MoE) VRAM requirements — by VRAMwise ↗