Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fleet Requirement Projection on Qwen3-235B workload (10,000 req/s on AMD MI300X)
Loading...
137
Nodes
Token-budget
134.6
150.8
167
183.2
Apr 9, 2026
Nodes
GPUs
Annual Cost
Annual Savings
Updated 9d ago
Evaluation Results
Method
Method
Links
Nodes
GPUs
Annual Cost
Annual Savings
Token-budget
Backbone Model=Qwen3-2...
2026.04
137
1,096
35.2
15.4
Homogeneous
Backbone Model=Qwen3-2...
2026.04
197
1,576
50.6
-
Feedback
Search any
task
Search any
task