<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[AI &amp; Software]]></title><description><![CDATA[CAD, generative AI, machine learning, and the software behind modern object design and engineering]]></description><link>https://forum.objects.foundation/category/12</link><generator>RSS for Node</generator><lastBuildDate>Sun, 12 Jul 2026 21:23:02 GMT</lastBuildDate><atom:link href="https://forum.objects.foundation/category/12.rss" rel="self" type="application/rss+xml"/><pubDate>Fri, 03 Jul 2026 21:23:49 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[PrismML]]></title><description><![CDATA[Bonsai 1 Bit
Announcement: https://prismml.com/news/bonsai-8b
Hugging Face: https://huggingface.co/prism-ml/Bonsai-8B-mlx-1bit
Bonsai 1 Bit is a 1 bit language model that comes in 8B, 4B, and 1.7B parameter sizes. The 8B model is 1/16 the size of comparable 16 bit 8B open models with similar performance. At 1.15gb, this model can fit on many kinds of devices with 4-5x better energy efficiency
]]></description><link>https://forum.objects.foundation/topic/11/prismml</link><guid isPermaLink="true">https://forum.objects.foundation/topic/11/prismml</guid><dc:creator><![CDATA[montez]]></dc:creator><pubDate>Fri, 03 Jul 2026 21:23:49 GMT</pubDate></item><item><title><![CDATA[Local LLMs]]></title><description><![CDATA[Google Gemma 4
Hugging Face: https://huggingface.co/collections/google/gemma-4
GitHub: https://github.com/google-gemma
Website: https://ai.google.dev/gemma/docs/core
Announcement: https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/, https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemma-4-12B/
Developer: Google DeepMind
Released: 26B A4B and 31B: April 2026 / 12B Unified: June 2026
Variants: 12B Unified, 26B A4B, 31B
Parameters: 12B Unified: 11.95B / 26B A4B: 25.2B total, 3.8B active / 31B: 30.7B
Context: 256,000 tokens
Architecture: 31B: Dense / 26B A4B: MoE, 8 active of 128 experts plus 1 shared / 12B: Unified encoder-free dense, multimodal input projected directly into the decoder
License: Apache 2.0
Modalities: 12B: Text + Image + Audio / 26B A4B and 31B: Text + Image
Runs on: Laptop, consumer GPU/workstation class
Formats: GGUF via Ollama/LM Studio, safetensors via Hugging Face, Docker
On disk: 12B: 7GB Q4, estimated / 26B A4B: 15GB Q4, estimated / 31B: 18GB Q4, estimated
]]></description><link>https://forum.objects.foundation/topic/10/local-llms</link><guid isPermaLink="true">https://forum.objects.foundation/topic/10/local-llms</guid><dc:creator><![CDATA[montez]]></dc:creator><pubDate>Fri, 03 Jul 2026 21:21:04 GMT</pubDate></item><item><title><![CDATA[CAD Kernels]]></title><description><![CDATA[libfive
Type: Implicit field based
Created: 2017
Website: https://libfive.com/
GitHub: https://github.com/libfive/libfive
]]></description><link>https://forum.objects.foundation/topic/9/cad-kernels</link><guid isPermaLink="true">https://forum.objects.foundation/topic/9/cad-kernels</guid><dc:creator><![CDATA[montez]]></dc:creator><pubDate>Fri, 03 Jul 2026 21:19:58 GMT</pubDate></item><item><title><![CDATA[Text to CAD]]></title><description><![CDATA[Text-to-CAD from Jake Fitzgerald
A collection of agent skills for CAD, robotics and hardware design
Website: https://www.cadskills.xyz/
GitHub: https://github.com/earthtojake/text-to-cad/blob/main/skills/cad/SKILL.md
X: https://x.com/earthtojake
Formats: STEP, DXF
Kernel: OpenCASCADE (build123d based)
Jake is a software engineer at South Park Commons.
]]></description><link>https://forum.objects.foundation/topic/5/text-to-cad</link><guid isPermaLink="true">https://forum.objects.foundation/topic/5/text-to-cad</guid><dc:creator><![CDATA[montez]]></dc:creator><pubDate>Fri, 03 Jul 2026 19:11:06 GMT</pubDate></item></channel></rss>