Articles tagged "DeepSeek V4"

DeepInfer is DeepSeek's Apache 2.0 inference engine (Oct 2026): V4.1-Flash on SM100 GPUs and Ascend 950 only. Requirements, setup, and differences from vLLM.

DeepSeek V4.1 Flash (1017) needs ~510GB for the official weights, ~430GB at 4-bit class: 8x H200 or a 512GB Mac. Updated Oct 2026: 763B vs 552B, memory by quant, API pricing.

DeepSeek V4.1-Flash launched Sep 10, 2026: 552B MoE, 8B/16B active params, 890-byte/token KV cache, quarter prior gen, MIT license. Pricing and VRAM specs.

DeepSeek's V4-Flash-Vision-Exp launched Aug 21, 2026 at V4-Flash pricing. On Aug 31, DeepSeek open-sourced the ~168GB FP4/FP8 weights on Hugging Face under MIT. Update covers local hardware needs and when the API still wins.

DeepSeek V4 Pro hit GA (V4-Pro-0813) Aug 12, 2026 with big benchmark gains. API prices rise Aug 16, output ~2.3x. Covers pricing, self-hosting, Harness v0.1.

DeepSeek V4-Flash needs roughly 160GB at 4-bit and V4-Pro about 920GB. The July 31 V4-Flash-0731 build keeps the same footprint while beating V4-Pro on agent benchmarks. VRAM, RAM and GPU tables by quantization, API pricing, and the legacy model retirement. Updated August 2026.

Overview of DeepSeek V4 Preview, released on April 24, 2026: two open-weight Mixture-of-Experts variants (V4-Pro at 1.6T total / 49B active and V4-Flash at 284B / 13B), 1-million-token context, weights on Hugging Face, and rollout via API and chat — based on official information.

A unified roundup of eight major AI releases that landed between April 16 and 24, 2026 — Claude Opus 4.7, Kimi K2.6 GA, Gemini 3.1 Pro Deep Research / Deep Research Max, Qwen 3.6-27B, GPT-5.5, DeepSeek V4 Preview, the open-sourcing of Japan's government AI Genai, and OpenClaw 2026.4.23 — with a take on what SMBs should think about.