#rtx-5090

The latest AI and developer news about #rtx-5090, with the original source and a short summary.

The open-source ORL method and dlmrt engine enable diffusion LLMs to reach 7,708 tokens/s on 8x B200 GPUs.

·2026.10.17 04:00

The production halt is expected to cause a supply drought that drives up prices, with the RTX 5080 24GB rumored to become the new gaming flagship.

·2·2026.10.11 00:00

The NInfer fork supports a 555k token context window on the RTX 5090 via NVFP4 KV cache and YARN extension.

·2026.09.06 07:00

In an RTX 5090 Llama.cpp experiment, MiniMax-M2.7 processed at 22 tps even at 100k context but only generated at 3~4 tps.

·1·2026.04.30 16:00

Qwen3.6-27B-INT4 achieved 256k context and 105~108 tps on a single RTX 5090.

·1·2026.04.26 17:00

Gemma4 and Qwen 3.5/3.6 were compared on RTX 5090 using the same document-writing task.

·2·2026.04.23 09:00

Qwen 3.6 35B A3B achieved 187t/s on an RTX 5090 32GB.

·1·2026.04.17 08:00