devtake.dev — #open-weightsArticles tagged open-weights on devtake.dev.https://devtake.dev/en-usRunning a coding agent fully on Apple Silicon, no cloud, is now an off-the-shelf stackhttps://devtake.dev/article/local-coding-agents-mac/https://devtake.dev/article/local-coding-agents-mac/A popular Hacker News how-to walked through a fully local coding agent on Apple Silicon. Here's the realistic 2026 stack: runner, model, and harness.Sat, 13 Jun 2026 12:30:00 GMTaiaillmlocal-inferenceai-agentsagentic-codingopen-weightsmacmoedieter-morelliCactus Compute distilled Gemini into a 26M tool-calling model. The trick: no feed-forward layers.https://devtake.dev/article/needle-cactus-compute-tool-calling/https://devtake.dev/article/needle-cactus-compute-tool-calling/Needle is a 26M-parameter function caller distilled from Gemini 3.1 Flash-Lite. The Simple Attention Network drops MLPs and runs at 6,000 tok/s prefill on edge silicon.Wed, 13 May 2026 10:00:00 GMTaiai-modelsgeminiopen-weightsfunction-callingtool-callingedge-aion-device-aismall-modelsdieter-morelliArcee's Trinity-Large-Thinking is a 399B open MoE that costs 96% less than Opushttps://devtake.dev/article/arcee-trinity-large-thinking-reasoning/https://devtake.dev/article/arcee-trinity-large-thinking-reasoning/Arcee released Trinity-Large-Thinking on April 1: a 399B-param sparse MoE with 13B active, Apache 2.0 weights, $0.88 per million output tokens, and PinchBench just behind Opus 4.6.Mon, 27 Apr 2026 13:00:00 GMTopen-sourcearceetrinityllmai-modelsopen-weightsmoereasoningapache-2-0soren-vanekOpenAI's Privacy Filter is a 1.5B PII redactor that ships under Apache 2.0. Here's what it actually does.https://devtake.dev/article/openai-privacy-filter/https://devtake.dev/article/openai-privacy-filter/OpenAI released Privacy Filter on April 22 as an open-weight on-device model for masking eight types of PII. F1 of 96%. Runs in a browser. Here's the catch.Sun, 26 Apr 2026 13:00:00 GMTaiopenaiprivacypiiopen-weightsai-modelsllmhugging-facedata-privacydieter-morelliDeepSeek V4 lands: 1.6T-param open MoE, 1M-token context, and SWE-bench within 0.2 of Opus 4.6https://devtake.dev/article/deepseek-v4-release/https://devtake.dev/article/deepseek-v4-release/DeepSeek shipped V4-Pro and V4-Flash under MIT on April 24. V4-Pro hits 80.6% on SWE-bench Verified. V4-Flash is $0.14 in / $0.28 out.Fri, 24 Apr 2026 21:30:00 GMTaideepseekdeepseek-v4llmai-modelsopen-weightsmoebenchmarksopen-sourcedieter-morelliQwen 3.6-35B-A3B: the open MoE beating Opus 4.7 on Simon Willison's laptophttps://devtake.dev/article/qwen-3-6-35b-a3b-beats-opus-on-laptop/https://devtake.dev/article/qwen-3-6-35b-a3b-beats-opus-on-laptop/Alibaba's Qwen 3.6-35B-A3B is a 35B-param mixture-of-experts with only 3B active. Apache 2.0, runs on consumer GPUs, and it's already winning real tasks.Fri, 17 Apr 2026 10:00:00 GMTaiqwenalibabaopen-sourcemoellmlocal-inferenceopen-weightsdieter-morelli