Full Stack R&D Developer Web Evangelist. Always looking to learn and improve my skills, while helping others do the same.
Tampa Fl.
Joined February 2010
- Tweets12.9K
- Following921
- Followers675
- Likes4.4K
Pinned Tweet
Finally finished my new site pretty happy with how it turned out and remember I'm open for work 😅 #WebDev #3D #Ai #Animation #NewSite
benmarte.com/
Benjamin Marte retweeted
Last Qwen3.8 Flash update with STQ 2.75bpw v2.0 pack. It moves away from hybrid affine/stq format to pure STQ with +15% quality. 64GB users can enjoy this while waiting for Qwen 4! Require Sushi 1.5.1 ro run.
👉 huggingface.co/beamster/Qwen…
Benjamin Marte retweeted
DeepSeek STQ 1.75bpw v2.0 is here! Custom tunings cut ~15% errors in every category, surpassing the much bigger oQ2.5e, yet runnable with 96GB+ Mac. Real demo as always, it rendered this Xmas magic weather simulations!
Grab it 🤗🍣 huggingface.co/beamster/Deep… (Require 🍣 1.5.0)
Benjamin Marte retweeted
Weights: huggingface.co/speridlabs/id…
Code: github.com/speridlabs/idol-s…
Try it: huggingface.co/spaces/sperid…
Benjamin Marte retweeted
A new tiling system for macOS
1. Apps in columns
2. Clickable icon for scrolling
3. Multi-monitor support
4. Built in performance monitor
5. MCP using Apple Intelligence for layout (native)
ckluis.github.io/kolom/
Benjamin Marte retweeted
You don’t need a Mac to build and install an iPad app.
Today my agent built and signed an app on Linux, then installed it over Tailscale with no USB cable.
No Mac in the build or install path.
It's all open source: github.com/joshuaswarren/oma…
Benjamin Marte retweeted
Tutorial on how to use /print3d:
- open your fav coding agent (hermes agent)
- post a picture/description of what you want
- wait a couple of minutes.
prompt: use /print3d to make this case [pic] for my raspberry 5 but with the possibility to stack them in a row
Benjamin Marte retweeted
This is REA for objects.
You see something you like and you can print it starting from a picture or a description
github.com/mfranzon/print3d
I love the intersection of the real world and software automation, I was finally able to finish my @home_assistant dashboard like I envisioned, I'm not gonna lie I might've gotten a bit carried away but it was super fun @wesbos #PhotoFame
Benjamin Marte retweeted
MLX-Serve 26.10.2 is out, download for your Mac/iOS/DGX/x86 - Same MLX Models now run everywhere.
Enable Lan Sharing and share across devices.
GLM 5.3, DS4.1, Mimo, MiniCPM, YuE2, and more.
github.com/ddalcu/mlx-serve/…
Benjamin Marte retweeted
Sushi 🍣 1.2.2 has landed with GLM5.3 Flash support for 96GB machine!
✅ ~79GiB, 10s load time.
✅ KLD 0.103 vs BF16 (code, prose avg at 512 tokens)
✅ 512k context (8 bits) / 300k context (BF16)
🤗 huggingface.co/beamster/GLM-…
Benjamin Marte retweeted
🚨🚨🚨
keys - TensorFold Studio ONE DGX-Spark + Mac M1-M5 (64GB ram min) v2.3 Released now also with Qwen2.1 Image Turbo integrated!!!!!!!!!!
Go Get It!!!!!!!!!!!!!!!!!!
if you like the repo and want to support please donate to: GoFundMe in Profile
github.com/drowzeys/keys-Ten…
Benjamin Marte retweeted
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
🤖 Made with AI
Benjamin Marte retweeted
GameToMac now supports 20 games running smoothly on Apple Silicon.
Next is more launchers: Epic, GOG, Battle net and Rockstar.
Then a bit more time on each game before adding new ones.
Benjamin Marte retweeted
Software engineers are supposed to do exactly what we’ve always done. Ensure that the composition and structure of the system is robust and maintainable and that the behavior of the system properly serves the needs of our users.
This requires engineering discipline. It need not require detailed reading of the code; just as using compilers does not require detailed reading of the binary.
Benjamin Marte retweeted
If you can write CSS, you can write GSS { ● }
I've been dreaming of this for years: a language to build 3D scenes like you write CSS. Selectors, cascade, :hover, keyframes… compiled to one GPU shader.
Meet GSS: GPU Style Sheets.
gss-lang.dev
#shader #glsl #gss
Benjamin Marte retweeted
Six months ago I had a hunch.
Local AI won't become the norm until it feels instant. Running a model on your own machine should feel like magic, not like tapping your fingers waiting for a reply.
The response to TensorFold since has blown me away. Thank you to everyone testing it, sending PRs and sharing feedback.
There's a lot more speed to unlock. Right now most of my time goes on reviewing and landing PRs. That matters, and every fix makes TensorFold better, but the biggest gains are in deep performance work I can't get to quickly.
If you want to see what TensorFold can really do, backing would let me work on it full time, with the hardware to test faster and dig into performance, and bring it to everyone in local AI.
All in the open under Apache-2.0.
We have been made aware that TF is being run in real production environments, so we could potentially look into support packages.
To back the project, sponsor hardware or talk about support, my DMs are open.
Even just sharing this post helps. 🫶🏼
