deepseek-v4.1POST

llama.cpp merges V4.1 Flash 1017 fix: 30.8 tok/s on 192GB M2 Ultra

DeepSeek's API now redirects V4 Flash Vision Exp calls to V4.1 Flash 1017; a llama.cpp fix made with the model on a 192GB M2 Ultra was merged, logging 28.1 minutes at 215 tok/s prompt and 30.8 tok/s output, with the smallest GGUF at 98.6GB.

Steven | SelfHostedSI

@SelfHostedSIArchived 2 days agoOriginally posted 2026.10.27

Steven | SelfHostedSI @SelfHostedSIOriginally posted 2026.10.27

Open original on X

DeepSeek retired V4 Flash Vision Exp on its API: calls to that name now get V4.1 Flash 1017. On Sunday Georgi Gerganov merged a llama.cpp fix he made with that same model, running on a 192GB M2 Ultra. His PR logs the run: 28.1 minutes, prompt at 215 tok/s, output at 30.8 tok/s, 39 lines added across 4 files. The weights are still on Hugging Face, smallest GGUF 98.6 GB. On your own disk, a model only changes when you swap the file.

x.com/selfhostedsi/status/2114769024429277507Archived 2026.10.27 12:09