Niko Veit (@coldniko)
Feed del autor de Strata.

Posts
- Project Maya deep dive: running GLM-5.3-Flash (321B MoE) on your own NVIDIA GPUs, built on Strata
- Small patch coming in approx 1h for this issue
- New release is out!
- @rskjr Hey Robert! I have seen your live stream and concerns in Strata and totally agree. Things are progressing a bit fast, just wanted to …
- @yue_neg_631 I have a surprise for that :))
- Strata wins by a tight margin against other Strix Halo inference engines on first try release
- @servasyy_ai Amazing work from you! I love the community and all the help I get with great PR's and benchmarks you are doing. I'll be lookin…
- @toolowgear @__kutluk Soon 👀👀👀
- Only loses to @ciruai engine on Hermes benchmarks. Kudos 🫡
- Strata wins by a tight margin against all other Strix Halo inference engines in it’s first try release. Did not expect that! 🥳 https://t.co…
- @joseed801 Yes
- @badguyty @LotusDecoder I have Aura, but it’s catching up on me 😭
- @Biggest I’m waiting @Alibaba_Qwen @QwenDevs 👀
- @shishimaimidori You are correct and it packs better power.
- @gabu3d_pl @pardoxAI I'm just doing tests on 4x cards. Hold up ;)
- @D3PR3C4T0R @AMD @ColbyCakesss @AzorFrank I'm dealing with Strata, I have finger crossed for you to handle it!
- @ibrahim_sanata5 Works steadily on 8GB
- Running Strata on Mini PC with iGPU 780M — about 13 tokens/s on first try
- @RRunner144 Get me SSH!!!
- @arnewc @forgalaforus There is a lot more to go.
- @sami3dat Need to get W7800 to optimize -.-
- @sami3dat Yes, but very soon optimized ;)
- @zharoboy Check my latest post :))
- @cryptodreki @LotusDecoder I will in 2-3 days tops
- Running Strata on Mini PC with iGPU 780M
- For those who slept on Qwen3.8-Flash-Next — community ts-bench comparisons vs 27B stacks
- Strix Halo officially supported in Strata v0.1.40
Interacciones
- Community call to support Strix Halo / Strata hardware outreach — Ecosystem voices (e.g. Zed) amplifying AMD community hardware for Strata development. source