Who Needs a GB300? Researcher Makes a Movie on a $500 16GB GPU
francoisfleuret · x · 2026-09-05
François Fleuret pushes back on top-end compute talk (GB300) by showing a movie generated on a $500 consumer GPU with just 16GB of VRAM, demonstrating local video generation on budget hardware.
More from Infra
- Dev Tests NVIDIA's Deepseek V4 NVFP4: 1M Context, 96% Memory at Batch 2048 — HankYeomans · 2026-09-05
- Minima quantizes all 496 layers of Qwen3.8-27B to NVFP4 W4A4, matching BF16 at 2.9x smaller — pbaylies · 2026-09-05
- 19 latency patterns to cut non-model latency in AI applications — bibryam · 2026-09-05
- Astra reportedly trained on 100,000 GPUs, a staggering compute scale — sudoraohacker · 2026-09-05
- GPT-6 reportedly trained on just 100K B200/300 GPUs at a single Texas facility — round · 2026-09-05
- gfx906-llama-cpp Fork Boosts MI50/MI60 Inference +23% Prefill, Fits 250k Context on 40GB — milpster · 2026-09-05