Re:Ask HN: Is anyone still working on dLLMs
by krooost on Thursday October 08, 2026 @03:35PM
(#50010888)
thanks for the feedback! would you mind sharing more details about your use case and setup? Mercury 2.5 should be much faster than Gemini 2.5 Flash - AA benchmarks output tokens per second of 617 vs 167). feel free to dm at [email protected] and I'll see if I can help.
[ Parent
| on HN ]
There are no comments on this comment yet.