FEED LIVE · STREAMINGUMTALE.LAB/POSTS
Category: AI
⌕⌘K
SORT
BLOGS · AI
Reviving the P104-100: Can E-Waste Mining GPUs Actually Run Modern AI?
A comprehensive P104-100 benchmark and comparison against the GTX 1070, RTX 2060S, RTX 3090, and RX 470. Exploring the Pascal architecture, KV cache quantization, and real-world performance in Gemma 4, Qwen 3.8 27B, Krea 2, and SDXL.
33 min// 001→
BLOGS · AI
NVIDIA CMP 170HX: How a VRAM unlock tool turned 'mining junk' into a hot AI hardware in few days
NVIDIA's CMP 170HX graphics card is experiencing a phenomenal resurgence thanks to the new CMPUnlocker tool, which unlocks up to 80GB of its memory.
4 min// 002→
BLOGS · AI
Local waifu on AMD Polaris: Running AI on an RX 470 when ROCm is dead
Discover how to run large language models (LLMs) on older AMD RX 470 (Polaris) graphics cards using KoboldCPP and Vulkan, with tips for optimizing performance and memory.
17 min// 003→
BLOGS · AI
Running Stable Diffusion WebUI on older AMD RX 400/500/Vega, R9 200/300 GPUs (Windows)
Get Stable Diffusion WebUI DirectML running on older AMD RX 400/500/Vega, R9 200/300 GPUs (Windows). This guide covers requirements, installation, and tackling 4GB+ VRAM issues.
12 min// 004→