Qwen Flash Next @ 137 tok/s & 3,497 tok/s Prefill w/ 512k context on a 5090, 192gb ram, Windows Build, comparing Strata and Infernix
英文标题:Qwen Flash Next @ 137 tok/s & 3,497 tok/s Prefill w/ 512k context on a 5090, 192gb ram, Windows Build, comparing Strata and Infernix
Strata vs Infernix on the same model, RTX 5090 — A/B at 262k and 512k context Hi folks, another inference engine post for your feed. I was blown away by Strata, but saw someone else post about Infernix with some wild claims, and it doesn't seem so well known, so I've spent a day downloading models a
中文
Strata vs Infernix on the same model, RTX 5090 — A/B at 262k and 512k context Hi folks, another inference engine post for your feed. I was blown away by Strata, but saw someone else post about Infernix with some wild claims, and it doesn't seem so well known, so I've spent a day downloading models a
中文全文翻译正在补齐,可先查看下方英文原文。
English / 原文
Strata vs Infernix on the same model, RTX 5090 — A/B at 262k and 512k context Hi folks, another inference engine post for your feed. I was blown away by Strata, but saw someone else post about Infernix with some wild claims, and it doesn't seem so well known, so I've spent a day downloading models a