» Tag
deepseek
9 postsSingle MI300X, Real Coding Agents: DeepSeek V4 Flash Throughput Tested
Real-world benchmark of DeepSeek V4 Flash on a single MI300X GPU serving coding agents, covering throughput, caching, and cost per token.
DeepSeek V4 Flash reaches 32 tok/s on AMD Ryzen AI MAX+ 395
AMD Ryzen AI MAX+ 395 runs 284B-parameter DeepSeek V4 Flash locally at 32 tok/s decode and ~250 tok/s sparse prefill using 128GB unified memory.
How We Self-Host DeepSeek V4 Flash on AWS Spot Instances
Inside a self-hosted DeepSeek V4 Flash deployment on AWS spot GPUs: MXFP4 quantization, RTX PRO 6000 hardware, DSpark decoding, and KV cache tuning.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.com10 AI Coding Models, 5 Tasks: Price Doesn't Predict Quality
Benchmarking 10 LLMs across 5 coding tasks reveals price and code quality barely correlate, with budget models rivaling premium ones.
antirez's DS4 engine: DeepSeek V4 Flash tops local coding on a MacBook Pro
DeepSeek V4 Flash via antirez's DS4 engine one-shots complex coding prompts on a MacBook Pro, outperforming other local models in real-world testing.
DeepSeek-V4-Flash 0731: Full Precision Lossless Performance Test
DeepSeek-V4-Flash-0731 can be run at full precision with 176 GB memory. The project focuses on efficiency and performance testing.
Enhance DeepSeek Harness with LLM-as-a-Verifier Plugin
The LLM verifier plugin for DeepSeek Harness grades candidate solutions and returns the best one.
DeepSeek Harness Launches as Open Source Rival to Claude Code
DeepSeek introduces DeepSeek-V4-Pro and open-source DeepSeek Harness, transforming software development.
Deepseek V4 Flash Achieves ~160 t/s on RTX 6000
Details on achieving ~160 t/s with Deepseek V4 Flash on RTX 6000 and setup information.