Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU
Fine-tuned Qwen on my 16gb GPU to respond without the letter e
Behold, Intel plans a 480GB GPU, a video card with more memory than the average laptop SSD has storage — but of course it's for AI, and curiously, it will use LPPDR5X, not even GDDR7
AMD's Radeon RX 9070 GRE graphics card returns to its lowest-ever price of $499 — rare deal places this current-generation 12GB GPU below its MSRP launch price
AirLLM 70B inference with single 4GB GPU
Lenovo wants $3,375 for a laptop with the GeForce RTX 5070 12GB GPU
Show HN: OSS implementation of Test Time Diffusion that runs on a 24gb GPU
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
New Huawei 96GB GPU
Run the strongest open-source LLM model: Llama3 70B with just a single 4GB GPU
