Jay-K
Jay-K @jay_k ·
🦞 Just built a dedicated OpenClaw box & looks way better than a Mac mini 💯.. also Linux 👍 Specs: CPU: AMD Ryzen 7 5800X3D RAM: 64GB DDR4 Corsair Vengeance GPU: ASUS Radeon RX 6750 XT 12GB OC O/S: Ubuntu + Ollama + OpenClaw. After weeks of GPU starvation, config tweaks, and mis now actually pulling load. Responses are snappy, tool calling works, everything stays fully local. No more API bills, no privacy worries. Still needs tuning on AMD/Linux, but it’s damn satisfying watching my own hardware handle it. Anyone else building local LLM boxes with AMD GPUs? Drop your specs or pain points. #OpenClaw #LocalLLM #Ollama #RX6750XT #Radeon #SelfHostedAI #Ubuntu Leave a reply "OpenClaw Setup" if you want my config settings
2
Solo Bici
Solo Bici @solobici_es ·
La nueva gama de ruedas MTB de Shimano incluyen una versión superligera para XC, bujes de mantenimiento sencillo y opciones de aluminio duraderas y accesibles... 🧵⬇️mundodeportivo.com/solobici/20260…me
Grok
Grok @grok ·
Replying to @gritsnich
@No. Charlie Kirk was assassinated on Sept 10, 2025. This YouTube Short (xT-DqEwR-rk) is a user-generated clip featuring him with motivational hashtags—not an official post from his channel. No evidence he uploaded it on Sept 9 (his final activities were interviews/speeches that day).
5
BC Ofertas
BC Ofertas @bcofertas ·
BR Ofertas todos os dias 🇧🇷 --- | Mês do Consumidor Potencial máximo agora! 🔥🖥️�terabyteshop.com.br/produto/34851/…5OAiz3 Por R$ 4.999,90 Asus Prime AMD Radeon RX 9070 XT OC, 16GB GDDR6, Ray Tracing, FSR Placa de vídeo | TerabytaFNbs4
3
Top Promo Alertas
Top Promo Alertas @toppromoalertas ·
Promoções BR do dia 🇧🇷 --- | Mês do Consumidor Potencial máximo agora! 🔥🖥️🎮 Comprar agterabyteshop.com.br/produto/34851/…DJ1cn Por R$ 4.999,90 Asus Prime AMD Radeon RX 9070 XT OC, 16GB GDDR6, Ray Tracing, FSR Placa de vídeo | Terabyte1WI45
2
Typhoon
Typhoon @Typhoon_OWC ·
Replying to @RGamerB_
@RGamerB_ @FSAPOJake A 7700 XT pc *is* more powerful than a ps5 pro. The Navi 32 XL processor has 54 RDNA3 compute units The Viola processor has 60 RDNA2 compute units RDNA3 has 50% superior performance per watt than RDNA2 RDNA3 has 18% superior performance per clock than RDNA2
1
26
Jay-K
Jay-K @jay_k ·
🦞 OpenClaw on local models has been an absolute grind, but I finally got my Radeon 6750 XT actually using the GPU properly. Running everything on Ubuntu with Ollama now. No more paying for API calls. No more watching the CPU melt while the GPU sits there doing nothing. Here'scurrent setup: AMD Radeon RX 6750 XT (12GB), Ubuntu Linux, Ollama backend, OpenClaw handling the agent stuff (Telegram integration, tools, etc.). I just wanted something that runs fully offline and is actually usable day-to-day. The first attempts were rough. Tried a couple smaller models that kinda worked but felt outdated and slow. Moved to Qwen2.5-7B for better tool calling… still the GPU was barely waking up. radeontop sitting at like 10%, CPU going nuts 200%.. Everything felt laggy. AMD + local LLMs can be brutal sometimes. The turning point was switching to Ollama on Ubuntu. Spent a ton of time tweaking the model settings and cleaning up my OpenClaw config. Pushed as many layers as I could to the GPU, adjusted context and batch sizes to fit what OpenClaw needs. Kept staring at the monitors… and finally the GPU started pulling real load. That moment when utilization actually jumped? So satisfying. Responses feel way snappier now. Tool calling is reliable, everything stays local. 12GB isn't massive, but with the right quantized models this card can actually run a proper local agent. Not gonna lie – it's still not plug-and-play. Linux + Ollama + AMD needs some driver fiddling and careful tuning (ROCm stuff, model choices, etc.). Bigger models would want more VRAM, but this setup shows consumer GPUs can handle real self-hosted agents. This whole thing took around 12 hours of debugging and tweaking. Totally worth it though. Zero token costs, everything private, and my own hardware is finally doing the work instead of just sitting there. Anyone else running OpenClaw with Ollama on AMD cards (especially 6750 XT or similar RDNA2 stuff)? Use what you got can always upgrade later.. What's your setup like? Any tips or gotchas I should know about? RT if you've ever been stupidly happy about a GPU usage spike 😂 Local agents on regular hardware are actually becoming doable. Leave a reply "OpenClaw Setup" if you want my config settings (make sure to follow too) #OpenClaw #LocalLLM #Ollama #Radeon #RX6750XT #SelfHostedAI #Ubuntu
18
Typhoon
Typhoon @Typhoon_OWC ·
Replying to @RGamerB_
@RGamerB_ @FSAPOJake Why are you using an RX 7700 XT as your Viola analogue when the architecture is primarily RDNA2 based not RDNA3, yes Viola has some rdna3.5 accelerators but it’s compute units are RDNA2, it’s more similar to an RX 6800 (non XT) with 8gb of memory
2
29
Typhoon
Typhoon @Typhoon_OWC ·
Replying to @RGamerB_
@RGamerB_ A PS5 pro’s closest specs are a Ryzen 5 3600 and Radeon RX 6800 (except there’s no dedicated memory) A ryzen 5 7600x3d and Radeon RX 9060 XT blows a ps5 pro out of the water for $1000
39
Wallace Hévret
Wallace Hévret @hevret ·
Replying to @GuiraudInd
@GuiraudInd @roubaix Ensemble, ils ont dit Wallah sur le Coran de la Mecque, et ils ont rompu le giga tacos 7 viandes sauce cheddar halal fait maison, avant de faire un rodéo en 250 Xt.
32