DeepSeek releases V4-Flash-Vision-Exp model
deepseek-ai · hf · 2026-08-31
DeepSeek released a new model, DeepSeek-V4-Flash-Vision-Exp. It features a text-generation pipeline with transformers architecture and supports safetensors. The model is available in 8-bit and fp8 formats, is endpoints compatible, and hosted in the US region under the MIT license.
More from Models
- Insider: Model Evals Interrupted Because Compute Was Reclaimed for Other Evaluations — sjgadler · 2026-08-31
- Developer Switches from Opus 5 to Codex Citing Better Performance — sirbayes · 2026-08-31
- Dots3-Note Weights Open: Addressing the Benchmark-Reality Gap — CodeByPoonam · 2026-08-31
- Tiel-Coder-35B-A3B Trends on HF with Speculative Decoding & MTP — peculiar-ragdoll · 2026-08-31
- Google Releases Gemini Omni 1.1 Flash, Updating Its Fast Multimodal Model for Developers — thione · 2026-08-31
- DeepSeek launches low-cost vision model; Anthropic previews hardware control protocol for agents — thione · 2026-08-31