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
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
0:15 6 354