Skip to content
Search
⌘
K
Models
Benchmarks
Chat
Rankings
Apps
Ori
Pricing
Docs
Models
Rankings
Ori
Benchmarks
Chat
Pricing
Docs
Sign Up
Sign Up
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
Private LLM hardware decision benchmark
Visit
Total tokens
4.34M
Daily global rank
—
Active since
Sep 2026
Models used
97
Private LLM hardware decision benchmark OpenRouter Usage
Last 30 days
Top models used by Private LLM hardware decision benchmark this month
1.
Qwen3.8 Flash
qwen
777K
tokens
2.
DeepSeek V4 Pro 0813
deepseek
454K
tokens
3.
GLM 5.3 Flash
z-ai
438K
tokens
4.
DeepSeek V4.1 Flash
deepseek
305K
tokens
5.
Granite 4.2 8B
ibm-granite
170K
tokens
6.
DeepSeek V4 Flash 0731
deepseek
163K
tokens
7.
Qwen3.8 2.4T A95B
qwen
114K
tokens
8.
Step 3.7 Flash
stepfun
107K
tokens
9.
Qwen3.8 Max (0902)
qwen
95K
tokens
10.
Laguna XS 2.1
poolside
89K
tokens
Show more