deepseek-ai/DeepSeek-V4.1-Flash · Hugging Face
5 experts across 2 network communities independently surfaced this.
“This graph is stunning: from huggingface.co/deepseek-ai/...”
“DeepSeek v4.1 Flash is just another level 🤯 huggingface.co/deepseek-ai/... - Asymmetric Causal-Encoder-Decoder: 550B MoE, input 8B / output 16B - Native vision merged into one endpoint - KV cache crushed: ~1/4 the HBM vs last one, 437× smaller than their fi…”