Model Releases
US-hosted, with Zero Data Retention enabled by default https://lmstudio.ai/models/deepseek-v4.1-flash
LM Studio is a US‑hosted platform that enables “Zero Data Retention” by default, meaning user inputs are not stored after processing. It currently hosts the DeepSeek V4.1 Flash model—a 552 B multimoda
LM Studio is a US‑hosted platform that enables “Zero Data Retention” by default, meaning user inputs are not stored after processing. It currently hosts the DeepSeek V4.1 Flash model—a 552 B multimodal mixture‑of‑experts neural network designed for coding, reasoning, visual understanding, and long‑context agents—with active parameters of 8 B or 16 B and a token context window of up to one million tokens. The model was released on September 11, 2026 (2:45 PM local time).
Related
- Now live in LM Studio Bionic!
- Currently serving 200 tps+ output speed for DeepSeek-V4-Flash on Ollama's cloud with zero data retention (ZDR). Have an amazing weekend 🫡
- DeepSeek-V4.1-Flash is now fully rolled out and available on Ollama's cloud: - Hosted in US & Europe - Zero data retention: prompts and resp…
Source: LM Studio (X) | 2026-09-11