I
Manufacturer
inclusionAI
Manufacturer profile and assigned models.
Best token generation
253,7 tok/s
Ling-3.0-flash
Best prefill
2.467,2 tok/s
Ling-3.0-flash
∅ Token generation
85,8 tok/s
Average of 65 runs
∅ Prefill
1.275,8 tok/s
Average of 65 runs
Best TTFT
1.505 ms
Ling-3.0-flash
Best harness rate
0%
no harness run yet
🏆
Ling-3.0-flash · fastest model at 253,7 tok/s token generation
Best prefill of this manufacturer: 2.467,2 tok/s (Ling-3.0-flash)
Best prefill of this manufacturer: 2.467,2 tok/s (Ling-3.0-flash)
Top models by token generation
Best measured generation throughput per model (tok/s), published performance benchmarks.