gpu4.pics show your rig · prove your tokens

Leaderboard

Generation speed ranked across accelerators — for a given model. Beautiful, not a spreadsheet.

Llama 3.2 1B Instruct 32Meta Llama 3.1 8B Instruct 14Qwen2.5 14B Instruct 12DeepSeek R1 671B 2Goliath 120B 2Qwen3 235B 2qwen3:14b 2
1
Apple M3 Ultra
512 GB ·community
18tok/s
—
2
NVIDIA RTX 3080
10 GB ·community
7.5tok/s
—