What GPU do you need to run gpt-oss-120b?

116.83B parameters, 5.1B active (mixture-of-experts) (Hugging Face, accessed 2026-10-15). Q4_K_M GGUF: 62.84 GB (source).

Single GPU that fits	VRAM	Speed estimate	Price
Apple Mac Studio M5 Ultra (64-core GPU, 96 GB)	96 GB	~332 tok/s	check price
Framework Desktop, AMD Ryzen AI Max+ PRO 495 (Strix Halo), 192 GB	192 GB	~76 tok/s	low $6,799 (new) source, 2026-10-16

Speed calculator estimate

GPU Count Model

Estimate = 0.76 × bandwidth ÷ GB read per token (Q4 file size, scaled by active/total parameters for MoE). Fit = file size + 1.5 GB headroom ≤ total VRAM. Multi-GPU: VRAM adds, speed uses one card's bandwidth (layer split). Short context only. How this works

Guide: Cheapest way to run gpt-oss-120b locally

What GPU do you need to run gpt-oss-120b?

Speed calculator estimate

Related