惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

酷 壳 – CoolShell
酷 壳 – CoolShell
aimingoo的专栏
aimingoo的专栏
P
Proofpoint News Feed
宝玉的分享
宝玉的分享
MyScale Blog
MyScale Blog
The GitHub Blog
The GitHub Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
月光博客
月光博客
量子位
博客园 - 司徒正美
V
V2EX
I
InfoQ
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Vercel News
Vercel News
H
Hackread – Cybersecurity News, Data Breaches, AI and More
美团技术团队
N
Netflix TechBlog - Medium
L
LangChain Blog
IT之家
IT之家
Blog — PlanetScale
Blog — PlanetScale
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Stack Overflow Blog
Stack Overflow Blog
A
About on SuperTechFans
Microsoft Azure Blog
Microsoft Azure Blog

Simon Willison's Weblog

Release: datasette 1.0a29 Thoughts on GitLab’s workforce reduction A quote from James Shore Your AI Use Is Breaking My Brain TIL: Using LLM in the shebang line of a script Learning on the Shop floor A quote from New York Times Editors’ Note A quote from Andrew Quinn A quote from Luke Curley Release: llm-gemini 0.31 Tool: Big Words Behind the Scenes Hardening Firefox with Claude Mythos Preview Notes on the xAI/Anthropic data center deal Tool: GitHub Repo Stats Live blog: Code w/ Claude 2026 Vibe coding and agentic engineering are getting closer than I’d like Release: datasette-referrer-policy 0.1 Release: datasette-llm 0.1a7 Release: llm-echo 0.5a0 A quote from Andy Masley April 2026 newsletter Research: TRE Python binding — ReDoS robustness demo Tool: Redis Array Playground A quote from Anthropic Sightings iNaturalist Sightings Codex CLI 0.128.0 adds /goal Our evaluation of OpenAI's GPT-5.5 cyber capabilities Quoting Andrew Kelley We need RSS for sharing abundant vibe-coded apps
Granite 4.1 3B SVG Pelican Gallery
2026-05-05 · via Simon Willison's Weblog

4th May 2026 - Link Blog

Granite 4.1 3B SVG Pelican Gallery. IBM released their Granite 4.1 family of LLMs a few days ago. They're Apache 2.0 licensed and come in 3B, 8B and 30B sizes.

Granite 4.1 LLMs: How They’re Built by Granite team member Yousaf Shah describes the training process in detail.

Unsloth released the unsloth/granite-4.1-3b-GGUF collection of GGUF encoded quantized variants of the 3B model - 21 different model files ranging in size from 1.2GB to 6.34GB.

All 21 of those Unsloth files add up to 51.3GB, which inspired me to finally try an experiment I've been wanting to run for ages: prompting "Generate an SVG of a pelican riding a bicycle" against different sized quantized variants of the same model to see what the results would look like.

Honestly, the results are less interesting than I expected. There's no distinguishable pattern relating quality to size - they're all pretty terrible!

Six different SVG images from models ranging in size from 1.67GB to 1.2GB. They are almost all an abstract collection of shapes - weirdly the smallest model had the best version of a bicycle, while the largest one had something that looked a tiny bit like a pelican.

I'll likely try this again in the future with a model that's better at drawing pelicans.