Stephen Thorn

[Joe Lowry @globallithium]

The back cover of Lithium Confidential. Hopefully I have the printers first copy to approve by the end of next week. Episode 235 of the podcast will be online tonight at 8:01pm eastern. A solo episode.

[Stephen Thorn @stephen_usmc]

@heyblake https://t.co/YWipC7ulkc

[Navy Athletics @NavyAthletics]

No better way to kick off Commissioning!

#GoNavy | @BlueAngels

[Navy Athletics @NavyAthletics]

Class of 2026 DISMISSED!

#GoNavy | @USNavy | @NavalAcademy

[Stephen Thorn @stephen_usmc]

Made the top 20 - pretty cool

[Hacker News 20 @betterhn20]

I automated opt-outs for 500 data broker sites (open source) https://t.co/lwyDqX9fMs (https://t.co/rbisXpXSDe)

[Tech Daily 24/7 @techdaily24]

I automated opt-outs for 500 data broker sites (open source) https://t.co/NnbH3kkEOY #startups #TechTrends

[Stephen Thorn @stephen_usmc]

@jawwwn_ @axios Last person im taking physical fitness advice from is this dude

[Stephen Thorn @stephen_usmc]

@0xSero something cool - https://t.co/YWipC7ulkc

[Jun Song @jun_song]

Some of the OG local LLM guys are stuck in the past.

I still see takes saying quantized models are bad.

No, new methods like DQ, TQ, and dynamic quants drop the loss.
You can shrink a model by multiple times and keep the loss under 1%.

Big model quantized > tiny model in BF16. It's not even a debate.

The local LLM scene a year ago vs today is a completely different universe.
Honestly, you can't even compare it to a month ago.

We have dozens of model options for every size now.
The dark ages of running weak early models that felt like a joke compared to cloud APIs are over.

Time to update your priors, accept the new meta, and admit your old takes might be wrong.

[dealign.ai @dealignai]

if you are a mlx inferencer maintainer, pls checkout https://t.co/QwSH3DPkCz - the fixes for dsv4 runtime are there with the prefix/paged cache working for the HSA/CSA/SWA attention combo. use this to get dsv4 coherent and working in ur engine.

[Stephen Thorn @stephen_usmc]

@hornsby_andrew @dealignai I will be running this soon. Curious to know what context size you're able to get? Are you using TurboQuant for the KV cache as well?

[Stephen Thorn @stephen_usmc]

Looking for 5 beta testers for #solollm to test new features before I release them. Comment or DM me your email for an invite

https://t.co/JoAub58iwz

[Stephen Thorn @stephen_usmc]

#SoloLLM in action fully disconnected. Local #AI #LLMs on iOS. It’s no Claude, but it sure is fun.

https://t.co/0CFgi8QnRA

[Stephen Thorn @stephen_usmc]

@MatthewBerman @nateherk @digitalix @TheCraigHewitt @AlexFinn @nicksaraev

[Stephen Thorn @stephen_usmc]

I built an AI app for iPhone where the AI runs 100% on your phone. Agent capabilities being built in v2.

No cloud. No account. No subscription. Works in airplane mode. Has options

13+ models. Built-in tools. MCP support.

$2.99 one-time.

Here's what it actually does 🧵

[Stephen Thorn @stephen_usmc]

https://t.co/7eYYjUeb8L

App Store (iPhone + iPad): https://t.co/2RmlwDhN8R

$2.99 one-time. No subscription. Works offline.

Happy to answer anything about how it works.

[Stephen Thorn @stephen_usmc]

Why I built it (besides just for fun)

Every AI app on my phone was sending my prompts somewhere else.
I wanted an AI that could actually do useful things - read my PDFs, run code,
search the web when needed, translate on-device - without handing all of that to a server.

[Stephen Thorn @stephen_usmc]

Privacy:

NEVER leaves your device:
- LLM inference (runs on your iPhone's chip)
- OCR, translation, code interpreter, file ops, clipboard
- All 13 models after download

Uses network only when you explicitly invoke:
- Web search / web fetcher
- Using your cloud subscriptions

[Stephen Thorn @stephen_usmc]

Many models across 6 families:

Gemma 4 / Llama / Qwen / Mistral / DeepSeek / Phi

Small models (1B–3B) for speed.
Mid-size (4B–7B) for “reasoning.”

No per-model unlocks. $2.99 gets you everything.

MCP support for connecting external tools if you want to go deeper.

[Stephen Thorn @stephen_usmc]

The tools are the part most local LLM apps don't have.

SoloLLM:

📄 PDF reader + document reader
✍️ File writer + extraction
🌐 Web search
💻 Code interpreter
📊 Data analyzer
🖼️ OCR
📋 Clipboard
🌍 Translation
🔗 Siri Bridge
📁 Files app integration