Show your rig. Prove your tokens.
A beautiful, open gallery of homelab & local-AI rigs — real tokens/sec, perf-per-watt, and cost, on the hardware people actually run. 70 rigs and counting.
▤ NVIDIA H100
80 GBLlama 3.2 1B Instruct· Q4_K_M· 1.5B
335
tok/s
▤ NVIDIA RTX A6000
48 GBLlama 3.2 1B Instruct· Q4_K_M· 1.5B
315
tok/s
▤ NVIDIA A100 80GB
80 GBLlama 3.2 1B Instruct· Q4_K_M· 1.5B
308
tok/s
▤ NVIDIA RTX PRO 6000 Blackwell Workstation Edition
95 GBLlama 3.2 1B Instruct· Q4_K_M· 1.5B
215
tok/s
▤ NVIDIA RTX 6000 Ada Generation
48 GBLlama 3.2 1B Instruct· Q4_K_M· 1.5B
131
tok/s
▤ NVIDIA H100
80 GBMeta Llama 3.1 8B Instruct· Q4_K_M
120
tok/s
▤ NVIDIA A100 80GB
80 GBMeta Llama 3.1 8B Instruct· Q4_K_M
110
tok/s
▤ NVIDIA RTX PRO 6000 Blackwell Server Edition
95 GBLlama 3.2 1B Instruct· Q4_K_M· 1.5B
106
tok/s
▤ NVIDIA RTX PRO 6000 Blackwell Workstation Edition
95 GBMeta Llama 3.1 8B Instruct· Q4_K_M
103
tok/s
▤ NVIDIA H200
141 GBLlama 3.2 1B Instruct· Q4_K_M· 1.5B
98.5
tok/s
▤ NVIDIA RTX A6000
48 GBMeta Llama 3.1 8B Instruct· Q4_K_M
90.5
tok/s
▤ NVIDIA H100
80 GBQwen2.5 14B Instruct· Q4_K_M· 14.8B
72.2
tok/s
▤ NVIDIA RTX PRO 6000 Blackwell Workstation Edition
95 GBQwen2.5 14B Instruct· Q4_K_M· 14.8B
70.8
tok/s
▤ NVIDIA A100 80GB
80 GBQwen2.5 14B Instruct· Q4_K_M· 14.8B
66.3
tok/s
▤ NVIDIA RTX A6000
48 GBQwen2.5 14B Instruct· Q4_K_M· 14.8B
52
tok/s
▤ NVIDIA RTX 6000 Ada Generation
48 GBMeta Llama 3.1 8B Instruct· Q4_K_M
51.3
tok/s
▤ NVIDIA RTX 6000 Ada Generation
48 GBQwen2.5 14B Instruct· Q4_K_M· 14.8B
28.1
tok/s
▤ NVIDIA RTX PRO 6000 Blackwell Server Edition
95 GBQwen2.5 14B Instruct· Q4_K_M· 14.8B
17.9
tok/s
▤ NVIDIA A100 80GB
80 GBGoliath 120B· GGUF8-BIT
12
tok/s