Inkling-2-Mini hits 170 tok/s on 2x3090s in local demos
LiTianleli · x · 2026-11-21
loktar00 shares a local demo of Inkling-2-Mini, calling it a fantastic local model and reporting 170 tok/s on 2x RTX 3090s, with 4x3090 setups in progress and more benchmarks promised. Another retweet adds that the model outperforms Qwen3 8B and is much faster with the right inference engine.
Related event: Inkling 2 Mini Benchmarks: ~200 tok/s on a Single RTX 4090(5 posts)→
More from Infra
- AI gateways are becoming the key control layer in production AI stacks: 8 capabilities — goyalshaliniuk · 2026-11-21
- Crowds line up to try local AI demos at NVIDIA RTX Spark launch — JFPuget · 2026-11-21
- Inkling-2-Mini quants are a trap: 17GB weights overflow 48GB VRAM at long context — EmilPi · 2026-11-21
- Cloudflare launches multimodal model clairic-flash, trending on Hugging Face — Cloudflare · 2026-11-21
- Hy AMA reveals Hy4 Flash runs on 96GB VRAM + 128GB RAM, plus QAT quantization details — allegedlyalienated · 2026-11-21
- Inkling-2-Mini runs on laptops with as little as 9GB RAM, per Unsloth local guide — NielsRogge · 2026-11-21