AI Briefing#rtx-3090
The latest AI and developer news about #rtx-3090, with the original source and a short summary.
The latest AI and developer news about #rtx-3090, with the original source and a short summary.
Running Mistral Medium 3.5 128B Q3_K_M locally on 3x3090 (72GB VRAM) measured 9.67t/s.
A reproducible setup was shared for running Qwen 3.6 35B MoE on an RTX 3090 with 262K context.
On 2x3090, a 250W power limit emerged as the efficiency sweet spot for Qwen3.6-27B.
In llama.cpp benchmarks, the Arc Pro B70 is significantly slower than the 3090, but SYCL improves things somewhat.
Ran Qwen3.6 35B 4bit for multi-user use via vLLM Docker on 2x RTX 3090.