Qwen3.5 35B-A3B sampling differs between Tinker API and Alibaba Cloud
philhchen · x · 2026-09-08
A developer reports that Qwen3.5 35B-A3B with image inputs produces very different sampling results on the Tinker API compared to the same model on Alibaba Cloud, suggesting platform-level inference differences for identical open-weight models.
More from Models
- Building a Model for Fancy Math and Code Is Easier Than One That Talks Like a Real Person — rickasaurus · 2026-09-08
- Bigger Context Windows Solve Fitting, Not Memory: Chroma's Context Rot Shows Accuracy Drops Early — Efficient_Joke3384 · 2026-09-08
- Codex Pro users report quota burning noticeably faster: 6% gone after one hour of use — yuntiandeng · 2026-09-08
- ProMax sweeps smartphones while AI model names go mythic — why the two industries diverged — APPSO · 2026-09-08
- What can you actually do with a small language model? Three real use cases — CurieuxExplorer · 2026-09-08
- Astra appears to access Sora via its CoT, one-shotting a generation — mallow610 · 2026-09-08