11 stories tagged with #5090, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "5090"
Retailer selling broken RTX 5090 GPUs for as low as $1,760 — GPUs were damaged during transport, but include all components on the PCB
A French retailer is willing to sell you defective RTX 5090s for half of what they cost new, on the condition that you'll be able to repair or recycle them. You can either get a ra…
You think frame generation boosts performance, but it exposes a bigger problem
What's the point of triple-digit FPS if you're still getting a double-digit experience?…
We tested supercharging the RTX 5090 in PhysX games using an RTX 5060 as a secondary GPU — SLI may be dead, but how much can dual GPUs boost performance in classic PhysX titles?
We're testing the impact of using a dedicated secondary RTX 5060 GPU to boost the performance of an RTX 5090 in a few classic Batman Arkham titles that support 32-bit PhysX.…
5090D V2 pc build - gaming purposes + longevity
Any and all advice welcome for rtx5090 build.
I just tested this $5,500 dual-screen gaming laptop with RTX 5090 power — here's what happened when I ran two games at once
Is the Asus ROG Zephyrus Duo worth $5,500? I tested this dual-screen gaming laptop by running two games simultaneously to see if it’s a beast or just a gimmick.…
Someone installed an e-ink stat display in their PC, and it looks gorgeous
The rest of the case is stunning, too.…
Pro 4500 vs downvolted 5090?
ASUS' dual-screen ROG Zephyrus Duo is now on pre-order starting at $4,500
ASUS is often best when it's weird, and this year at CES the company decided to resurrect one of its weirdest laptops ever: the ROG Zephyrus Duo.…
Qwen3.6-27B-INT4 clocking 100 tps with 256k context length on 1x RTX 5090 via vllm 0.19
Thanks to the community the Qwen3.6-27B speed keeps getting better. The following improves upon my recipe from yesterday and delivered a whopping 100+ tps (TG). Model: - MTP suppor…
Qwen3.6-27B at ~80 tps with 218k context window on 1x RTX 5090 served by vllm 0.19
Qwen3.6-27B is out for a few days and the NVFP4 with MTP is dropped earlier on HF: Can follow the same recipe I used for Qwen3.5-27B to achieve ~80 tps on a single RTX 5090 at 218k…