@maks6361 Are you posting via API? If so, an aggregator or direct platform APIs?
How are you warming up accounts at scale? Do you ever have to lighten up the posting due to shadowban and too consistent of a posting schedule etc.?
Convince me that I shouldn’t return the 96gb M5 ultra Mac Studio. Tried many engines but due to concurrency of even 2 agents destroying performance I can’t seem to justify it over just cloud subs 🤔
Qwen3.8-27B, up to 144 tok/sec on M5 Max.
Let that sink in. ⚡️✨🚀
Excited to partner with @inco_ai to bring you their Splash inference engine in LM Studio on day 0!
Get it running now: https://t.co/ZeCPIKw20o
@jun_song Prefill seems roughly the same as oMLX for me but on m4 pro 48gb I’m getting 130 TPS with minimal input, and it does quickly degrade. Still solid though, the A3B was able to get TTFT to around 20 seconds for 12k input context
This is how I got 1M users in 6 months
Finally dropping it! It's 60 pages lol
https://t.co/2qcH9lsUOM
If you repost & follow, I'll send you some extra sauce🌶️