Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Strix Halo in Framework desktop cluster working quite nicely with MiniMax-M2

digitalix's profile picture

Alex Ziskind

23,078 subscribers

20,334 Aufrufe • vor 11 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

We punished Intel's new Panther Lake processor with demanding ray-traced gaming benchmarks. How does it stack up against Strix Halo/Strix Point - and what about desktop GPUs like the RTX 3050 and RX 6600? Spoilers: we were impressed.
0:49

We punished Intel's new Panther Lake processor with demanding ray-traced gaming benchmarks. How does it stack up against Strix Halo/Strix Point - and what about desktop GPUs like the RTX 3050 and RX 6600? Spoilers: we were impressed.

Digital Foundry

84,700 Aufrufe • vor 9 Monaten

Halo 3 is in fact, quite back.
0:23

Halo 3 is in fact, quite back.

GhostSnacksType4

551,982 Aufrufe • vor 5 Tagen

Want to use the latest cool AI models inside TRAE? You can now connect and run MiniMax-M2 (or any other OpenRouter model) in just minutes. This tutorial walks you through: - Setting up OpenRouter service provider - Adding your api key in TRAE - Selecting MiniMax-M2 in chat or coding mode — and building a 3D object with Three.js! Watch the full walkthrough ↓
3:21

Want to use the latest cool AI models inside TRAE? You can now connect and run MiniMax-M2 (or any other OpenRouter model) in just minutes. This tutorial walks you through: - Setting up OpenRouter service provider - Adding your api key in TRAE - Selecting MiniMax-M2 in chat or coding mode — and building a 3D object with Three.js! Watch the full walkthrough ↓

TRAE

16,445 Aufrufe • vor 11 Monaten

Ryzen AI Halo launched today, but it's the software that benefits all strix halo systems. Finding if I go off script I can clear 1200t/s prompt processing with the latest software updates! How-to soon...
1:10

Ryzen AI Halo launched today, but it's the software that benefits all strix halo systems. Finding if I go off script I can clear 1200t/s prompt processing with the latest software updates! How-to soon...

wendell

40,987 Aufrufe • vor 3 Monaten

got desktop mate working with my lumi \o/ #VRChat #furry
0:27

got desktop mate working with my lumi \o/ #VRChat #furry

rossie

25,312 Aufrufe • vor 1 Jahr

introducing ADHD coding spawn unlimited agents in parallel each is working in isolation from its own computer in the cloud producing changes we can truly interact with, feel, debug via desktop streaming now we just switch desktop, criticize, switch desktop, criticize, merge
0:30

introducing ADHD coding spawn unlimited agents in parallel each is working in isolation from its own computer in the cloud producing changes we can truly interact with, feel, debug via desktop streaming now we just switch desktop, criticize, switch desktop, criticize, merge

Anicet

15,920 Aufrufe • vor 7 Monaten

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.
6:01

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

Santiago

91,263 Aufrufe • vor 11 Monaten

We found a great use case for OpenClaw🦞 running locally on a Framework Desktop with Fedora Project (@fedora@fosstodon.org)!
2:15

We found a great use case for OpenClaw🦞 running locally on a Framework Desktop with Fedora Project (@[email protected])!

Framework

47,026 Aufrufe • vor 7 Monaten

MULTIPLAYER WORKING IN MINECRAFT CONSOLE DESKTOP SOURCE CODE RELEASE FINALLY HOLY
0:30

MULTIPLAYER WORKING IN MINECRAFT CONSOLE DESKTOP SOURCE CODE RELEASE FINALLY HOLY

coah

1,975,167 Aufrufe • vor 7 Monaten

🔔 We're back with the second episode of Notable Commits! From framework updates to major upgrades in desktop performance and developer tooling, this July 2026 recap showcases how Google and the global Flutter community are advancing the framework together.
8:35

🔔 We're back with the second episode of Notable Commits! From framework updates to major upgrades in desktop performance and developer tooling, this July 2026 recap showcases how Google and the global Flutter community are advancing the framework together.

Flutter

12,742 Aufrufe • vor 1 Monat

i built an ipod inspired yt music desktop client using MiniMax (official) and opencode in 1 night 100% rust. check it out
0:45

i built an ipod inspired yt music desktop client using MiniMax (official) and opencode in 1 night 100% rust. check it out

shydev

15,971 Aufrufe • vor 8 Monaten

This change reflects quite nicely when opening the model in Quickview on Vision Pro
0:32

This change reflects quite nicely when opening the model in Quickview on Vision Pro

Brad Lynch

14,548 Aufrufe • vor 6 Monaten

GNOME Declares War on Framework Computer GNOME OS Team says Framework "supports Fascist and Racist s***heads", "does not feel comfortable in further collaboration". GNOME Board wants to talk to groups "reconsidering working with Framework".
19:09

GNOME Declares War on Framework Computer GNOME OS Team says Framework "supports Fascist and Racist s***heads", "does not feel comfortable in further collaboration". GNOME Board wants to talk to groups "reconsidering working with Framework".

The Lunduke Journal

44,721 Aufrufe • vor 11 Monaten

Introducing Halo, the best framework for post-training of open-source models. Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace format. Star us on GitHub:
0:42

Introducing Halo, the best framework for post-training of open-source models. Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace format. Star us on GitHub:

White Circle

2,335,934 Aufrufe • vor 22 Tagen

Took the good work of the communtiy of DwarfStar and consolidating the Strix Halo support. It looks very good. More QA in the next days and the final merge soon.
1:20

Took the good work of the communtiy of DwarfStar and consolidating the Strix Halo support. It looks very good. More QA in the next days and the final merge soon.

antirez

17,567 Aufrufe • vor 4 Monaten

working with binaryninja on an single ASAN output, of a sophisticated framework.
0:50

working with binaryninja on an single ASAN output, of a sophisticated framework.

ruikai

20,494 Aufrufe • vor 1 Jahr

We're working on WebGL support in Ladybird and it's progressing nicely.. In fact, Lubrsi just got Shadertoy working! 🤩🤯
0:44

We're working on WebGL support in Ladybird and it's progressing nicely.. In fact, Lubrsi just got Shadertoy working! 🤩🤯

Andreas Kling

14,797 Aufrufe • vor 1 Jahr

Can I interest anyone in the San Siro? #FM26 stadium modding is getting along quite nicely :D
0:44

Can I interest anyone in the San Siro? #FM26 stadium modding is getting along quite nicely :D

BassyBoy

17,695 Aufrufe • vor 10 Monaten

DeepSeek R1 (the full 680B model) runs nicely in higher quality 4-bit on 3 M2 Ultras with MLX. Asked it a coding question and it thought for ~2k tokens and generated 3500 tokens overall:
1:28

DeepSeek R1 (the full 680B model) runs nicely in higher quality 4-bit on 3 M2 Ultras with MLX. Asked it a coding question and it thought for ~2k tokens and generated 3500 tokens overall:

Awni Hannun

997,359 Aufrufe • vor 1 Jahr