Hackernews posts about an RTX 3090
- Over 1k tok/s on an RTX 5090 with Qwen3 0.6B (blog.alpindale.net)
- LLM from scratch, part 28 – training a base model from scratch on an RTX 3090 (www.gilesthomas.com)
- Counter-Strike's Dust II runs purely within a neural network on an RTX 3090 (www.tomshardware.com)
- Rent compute and run Ollama on an RTX 3090 – in one place (app.hyperbolic.xyz)
- Show HN: ZigNet: How I Built an MCP Server for Zig in 1.5 Days (fulgidus.github.io)
- Benchmarks show even an old Nvidia RTX 3090 is enough to serve LLMs to thousands (www.theregister.com)
- Show HN: GLM-Image Online – 16B AR+Diffusion model for accurate text (glmimage.online)
- Running Qwen3:30B MoE on an RTX 3070 laptop with Ollama (blog.kekepower.com)
- Show HN: Real-time 4D Julia set navigation via gamepad (banditcat.github.io)
- Show HN: I’ve made a real-time 3D fluid simulation in WebGPU (splash-fluid.netlify.app)
- Bride surprises new husband with an RTX 5090 on wedding day (www.tomshardware.com)
- Show HN: LTXV 13B Distilled – Generate 5s Videos in Under 10s (www.lightricks.com)