deepseek-v4.1POST

DeepSeek V4.1 Flash 1017 on 4x RTX 6000 Pro vs GLM 5.3 Flash

The author benchmarks V4.1 Flash 1017 with YourLocalAILab's vLLM fork on four RTX 6000 Pro GPUs against a GLM 5.3 Flash setup, concluding the new DeepSeek model is now their local default.

Austere

@commanderdata85Archived 10 days agoOriginally posted 2026.10.18

Austere @commanderdata85Originally posted 2026.10.18

Open original on X

Sharing the results of my own testing using @YourLocalAILab’s fork of vLLM with the new DeepSeek V4.1 Flash 1017 model, and comparing to my current setup with GLM 5.3 Flash. In short, the new DeepSeek model is now my local model of choice on a server with 4x RTX 6000 Pro GPUs. https://github.com/commdata2338/deepseek-v4.1-flash-1017-4x-rtx-pro-6000-benchmark

x.com/commanderdata85/status/2111679772711321680Archived 2026.10.18 16:44