Google: Gemma 4 26B A4B Performance
Try Gemma 4 26B A4B on us. Starter credit covers your first requests, then one key reaches all 11 provider routes with automatic failover.
google/gemma-4-26b-a4b-it
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for Google: Gemma 4 26B A4B . Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| wandb | 911 ms | 911 ms | — | 100.00% | — | 1 |
| nextbit | 1253 ms | 2160 ms | — | 100.00% | — | 7 |
| scaleway | 1336 ms | 1397 ms | — | 100.00% | — | 2 |
| parasail | 1589 ms | 1866 ms | — | 100.00% | — | 3 |
| nextbit-eu | 1626 ms | 2065 ms | — | 100.00% | — | 9 |
| muna | 1802 ms | 2265 ms | — | 100.00% | — | 5 |
| cloudflare-workers-ai | 2805 ms | 2805 ms | — | 100.00% | — | 1 |
Full provider & model leaderboard.
11 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.