Filter by tag

#deepseek

16 materials

OpenCode Boosts DeepSeek Efficiency 30× – $10 Gets $300 Power

OpenCode’s co‑founder reveals a method to make DeepSeek 30 times more cost‑effective – $10 now delivers the performance that used to cost $300.

cpaua15h ago1 min24

Nvidia DeepSeek Model Optimization

NVIDIA releases DeepSeek V4.1 1017: 81 GB smaller, same performance

NVIDIA's DeepSeek‑V4.1‑Flash‑1017 model is 81 GB smaller with only a 0.7‑point drop in Terminal‑Bench and 0.26 in SciCode, keeping near‑original performance for production inference.

cpaua3d ago1 min72

OpenCode Claude DeepSeek

OpenCode Update: Claude Subscription, DeepSeek Limits, Image Tool

OpenCode adds Claude subscription, raises DeepSeek V4.1 limit to $100 on the $10 Go plan, and adds an image generation tool for OpenAI, Gemini, Grok, etc.

cpaua5d ago1 min202

DeepSeek Large Language Models Quantization

DeepSeek V4.1-Flash 763B Runs Locally on 12GB GPU with Quantization

DeepSeek V4.1-Flash (763B) runs on consumer GPUs with 12 GB VRAM using GSQ‑RCO quantization, reaching up to 231 tokens/s input processing, but requires ~239 GB storage.

cpauaOctober 25, 2026 at 08:58 AM2 min260

DeepSeek DeepInfer Inference Engine

DeepSeek Open Sources DeepInfer Engine for Faster, Cheaper Inference

DeepSeek has released the source code of DeepInfer, its inference engine, on GitHub. The open‑source tool speeds up model serving, lowers costs and runs on Nvidia and Huawei hardware.

cpauaOctober 20, 2026 at 01:13 PM1 min142

DeepSeek AI Models API

DeepSeek V4.1 Flash 1017: 244 tps, $500/mo, Free API Search Till Oct 31

DeepSeek V4.1 Flash 1017 delivers 244 tokens per second, beating GPT‑6.1 Sol, priced at $500/month. Its web‑search API is free until Oct 31, then $0.75 per 1k requests.

cpauaOctober 17, 2026 at 12:45 PM1 min354

DeepSeek Large Language Models AI API

DeepSeek 4.1-1017 AI Model Rivals Opus 5 with 1M Token Context

DeepSeek 4.1-1017 matches Opus 5, excels in 3D, coding, agents, visual tasks, offers a 1M‑token window, cheap pricing, and is available via app, web and API.

cpauaOctober 17, 2026 at 10:22 AM1 min200