Applied Compute(@appliedcompute):A 35B open-weight model trained to search a precomputed index answers repo search questions at 100x lower cost than a frontier model. We partnered with @turbopuffer to train Qwen3.6-35B-A3B to find code across ~9,000 repositories. It tops the needle-in-a-haystack task outright at 2-10x lower latency.

Applied Compute

@appliedcompute

The best AI is built, not bought. Our platform, Applied Compute Agent Cloud, is now in private beta. Book a demo below.

加入 July 2012

25 正在關注 8.1K 粉絲

Applied Compute@appliedcompute

2026.09.04 17:48

A 35B open-weight model trained to search a precomputed index answers repo search questions at 100x lower cost than a frontier model. We partnered with @turbopuffer to train Qwen3.6-35B-A3B to find code across ~9,000 repositories. It tops the needle-in-a-haystack task outright at 2-10x lower latency.