003: Quad Radeon AI Pro R9700 (128GB VRAM) llama.cpp benchmarks
Let's see how larger models perform in llama.cpp on a quad Radeon AI Pro R9700 system. Also included are the same models benchmarked on a triple RTX A4000 system. https://github.com/tmac1973/llama-toolchest
▶︎
Dual AMD Radeon 9700 AI PRO: Building a 64GB LLM/AI Server with Llama.cpp
▶︎
I Tested the Cheapest Path to 96GB of VRAM
▶︎
How Floating-Point Rounding Lets a Model Tell Which Chip It's On — And Misbehave
▶︎
Valve Steam Machine Review: GPU & CPU Benchmarks, SteamOS Test, Thermals, Noise, and Price
▶︎
ECU is MESSING WITH HOLGER! 😮💨
▶︎
Creator of C++: Bell Labs, Negative Overhead Abstraction, Mistakes | Bjarne Stroustrup
▶︎
Intel Arc Pro B70 (32GB) for Local LLMs: llama.cpp (SYCL/Vulkan), vLLM (Intel LLM Scaler) Benchmarks
▶︎
DIY 25cc 4-Stroke Generator
▶︎
Android 17 sucks. So I put Linux on a phone.
▶︎
Creating a 48GB NVIDIA RTX 4090 GPU | Brother Zhang's Repair Shop (ft. 张哥)
▶︎
Their Company Data Is Trapped On This BitLocker-Encrypted SSD
▶︎
AMD MI50 32GB for Local AI: Qwen 3.6 & Gemma 4 on llama.cpp / vLLM (vs R9700)
▶︎
Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026
▶︎
تلاوة القرآن للدراسة والتركيز 📚🕛 | راحة وطمأنينة | Peaceful Focus Quran | محمد هشام
▶︎
Radeon R9700 Dual GPU First Look — AI/vLLM plus creative tests with Nuke & the Adobe Suite
▶︎
ARC Pro B70 vs Radeon AI PRO R9700
▶︎
Rock 4D: Excellent Arm SBC with PCIe connector
▶︎
NVIDIA didn't want me to do this
▶︎
Why the US Navy's "Dead" Railgun Just Fired Again
▶︎