What GPU do you need for Qwen3.8, Qwen3.6, Gemma 4 and gpt-oss locally? (measured, Oct 2026)

Automated excerpt

Gemma 4 12B at 38.5 tok/s, gpt-oss 20B at 84 tok/s Qwen3.6 35B-A3B at 140–153 tok/s on a 3090; Qwen3.8 27B at 40.4 tok/s (72.5 with MTP) on a 3090; Gemma 4 31B at 43.8 tok/s on a 4090 Qwen3.6 35B-A3B at 258, Qwen3.8 27B at 75.2, Gemma 4 31B at 70 tok/s gpt-oss 120B at 196 tok/s (Pro 6000) / 79.7 tok/s (M2 Ultra) 1. gpt-oss 20B: the one model everyone has benchmarked gpt-oss 20B runs in its native MXFP4 format, so these numbers compare well across cards.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.