Fastest Model
—
Top Tokens/sec
—
Lowest TTFT
—
Models Measured
—
| # | Model | Provider | Tokens/sec | TTFT | Latency | Throughput Bar |
|---|---|---|---|---|---|---|
| Loading speed metrics... | ||||||
What do these metrics mean?
Tokens/sec (TPS)
The number of tokens generated per second. Higher is better — this directly affects how fast you receive responses from the model.
Time to First Token (TTFT)
How long until the model starts generating its response. Lower is better — critical for interactive chat and streaming applications.
Latency
Total round-trip time for a simple request. Lower is better — includes network overhead and processing queue time.