DeepSeek-V4.1-Flash hits Ollama: 552B MoE backbone with 1M context via KV cache compression
ollama · x · 2026-09-11
DeepSeek-V4.1-Flash is now available on Ollama (cloud mode). The multimodal MoE model has a 552B backbone and supports up to 1M-token contexts, with vision, tools, and thinking modes.
- It uses a Causal Encoder-Decoder (CED) design — a 20-layer causal encoder stacked on a 20-layer decoder — with KV cache compression as the headline innovation for long-context efficiency.
- Pricing: $0.15/1M input, $0.003/1M cached input, $0.60/1M output.
- It plugs directly into Claude Code, OpenCode and other agent tools via ollama launch.
Related event: DeepSeek launches V4.1-Flash: 552B backbone, 1M-token context(5 posts)→
More from Infra
- DeepSpeed shows AutoEP/AutoTP/AutoSP parallelism gains, hosts office hours — PyTorch · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- Gary Marcus: With Q3 data added, Anthropic's compute-efficiency growth shows deceleration — GaryMarcus · 2026-10-27
- Inference is just Kubernetes with a multi-trillion-dollar market, and the communities overlap — matt_slotnick · 2026-10-27
- vLLM eyes Rust migration as inference engines race to rewrite the stack — AccBalanced · 2026-10-27
- Resin lets an agent build standalone LLM inference engines; vLLM and SGLang optimize DeepSeek kernels differently — AccBalanced · 2026-10-27