deepseek-v4.1POST

Running Qwen, GLM and DeepSeek V4.1 Flash locally on an RTX 3090

The author recalls only hoping to run Qwen3.6-27B on a used RTX 3090 in June, and now runs Qwen3.8-Flash-Next, GLM-5.3-Flash and, barely for now, DeepSeek V4.1 Flash 1017.

@ItsmeAjayKVArchived 10 days agoOriginally posted 2026.10.22

AJ @ItsmeAjayKVOriginally posted 2026.10.22

Open original on X

The models i'm running now on my RTX 3090 was an impossible dream just few months ago. When i bought my used 3090, back in June, all i ever wanted was to run Qwen3.6-27B ! Now i'm running - Qwen3.8-Flash-Next - GLM-5.3-Flash - DeepSeek-v4.1-Flash-1017 (barely for now, will get better👀) Models are getting better ! Inference engines getting better ! All of this is giving my 3090 a solid place in Local AI.

This post quotes another post: x.com/lottolabs/status/2112933213194891674

x.com/itsmeajaykv/status/2112958477765423322Archived 2026.10.22 12:01