Qwen: Qwen3.6 35B A3B Performance
Try Qwen3.6 35B A3B on us. Starter credit covers your first requests, then one key reaches all 14 provider routes with automatic failover.
qwen/qwen3.6-35b-a3b
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for Qwen: Qwen3.6 35B A3B. 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 |
|---|---|---|---|---|---|---|
| akashml | 792 ms | 2243 ms | — | 100.00% | — | 8 |
| atlas-cloud | 839 ms | 1116 ms | — | 100.00% | — | 2 |
| alibaba | 1111 ms | 1111 ms | — | 100.00% | — | 1 |
| siliconflow | 1149 ms | 1670 ms | — | 100.00% | — | 2 |
| boundless | 1473 ms | 1473 ms | — | 100.00% | — | 1 |
| wandb | 1474 ms | 1474 ms | — | 100.00% | — | 1 |
| io-net | 1548 ms | 1548 ms | — | 100.00% | — | 1 |
| featherless | 1597 ms | 3820 ms | — | 100.00% | — | 2 |
| streamlake | 2101 ms | 2741 ms | — | 100.00% | — | 3 |
| engy | 2198 ms | 2415 ms | — | 100.00% | — | 4 |
Full provider & model leaderboard.
14 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.