Pico AI Server and Pico AI Studio

One click install local AI server.

Discord:

[Pico AI Server and Pico AI Studio @PicoGPT]

Apple Silicon + Gemma 4 fans: this is for you.

Pico AI Server now supports continuous batching with MLX-Swift.

43 tok/s on 1 stream.
26 tok/s per stream on 2 concurrent streams.

That’s 52 tok/s total. a 21% throughput gain on a six-year-old MacBook Pro M1 Max!

[Pico AI Server and Pico AI Studio @PicoGPT]

Congrats @MiniMax_AI on the release! No word yet on the number of parameters, but Pico will support M3 when the weights are available on HuggingFace.

[MiniMax (official) @MiniMax_AI]

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities

- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- Natively Multimodal from Step Zero

API: https://t.co/fHRdSV7BwZ
Token Plan: https://t.co/BDCycxepZw
🚀New! MiniMax Code: https://t.co/GvB4YiB6Ul

Weights & Tech Report in ~10 Days

[Pico AI Server and Pico AI Studio @PicoGPT]

Download for free: https://t.co/oKjA8AlpXB

[Pico AI Server and Pico AI Studio @PicoGPT]

You know what doesn’t have monthly credits? Local AI 😏

[Matt Pocock @mattpocockuk]

Anthropic has given us a "dedicated monthly credit"

Which, in effect, slashes AFK usage limits of Claude Code by ~5-20X

Here's how it affects you:

[Ronald Mannak @ronaldmannak]

Huge shoutout to @PrismML

This shouldn’t be possible: a tiny model punching way above its weight.

The largest version is just 1.14 GB, which means it’s small enough for a phone.

Fast on a phone (spoiler: Pico for iOS is coming soon!). Insanely fast on a MacBook Pro M1 Max.

[Pico AI Server and Pico AI Studio @PicoGPT]

Download or update Pico AI Server today:
https://t.co/nvkPlZYseA

[Pico AI Server and Pico AI Studio @PicoGPT]

Pico Local AI Server 1.4.21 is now available on the Mac App Store. This release adds support for Ternary Bonsai, a lightning-fast model that outperforms many much larger models

[PrismML @PrismML]

Today we’re announcing Ternary Bonsai: Top intelligence at 1.58 bits

Using ternary weights {-1, 0, +1}, we built a family of models that are 9x smaller than their 16-bit counterparts while outperforming most models in their respective parameter classes on standard benchmarks.

We’re open-sourcing the models under the Apache 2.0 license in three sizes: 8B (1.75 GB), 4B (0.86 GB), and 1.7B (0.37 GB).

[Pico AI Server and Pico AI Studio @PicoGPT]

How fast you ask? About 109 tokens per second on an M1 Max MacBook Pro fast.

[NightMustEnd @NightMustEnd]

おー、ためす

[Ronald Mannak @ronaldmannak]

Excited to share that @awnihannun, co-creator of MLX, is joining AiOS Meetup 2026 for a special talk in Cupertino on June 11

Come hang with @RayFernando1337, @rudrank and folks building at the intersection of AI and Apple platforms. RSVP here:

https://t.co/hGnTOOhCoS

[Pico AI Server and Pico AI Studio @PicoGPT]

If you haven’t already, please rate the app on the App Store. It helps more people discover it. We’re at 4.6 in the U.S. and 4.5 worldwide, help us raise that

https://t.co/PQkCSDv6CY

[Pico AI Server and Pico AI Studio @PicoGPT]

If you haven’t already, please rate the app on the App Store. It helps more people discover it. We’re at 4.6 in the U.S. and 4.5 worldwide, help us raise that

https://t.co/PQkCSDv6CY

[Pico AI Server and Pico AI Studio @PicoGPT]

Welcome to all our new followers! Need support or have a feature request? Join our Discord: https://t.co/22ZZQwWtuD

[Ivan Fioravanti ᯅ @ivanfioravanti]

Pico AI Server another one to be added to my engine benchmarks! Be ready for some feedback @ronaldmannak 💪

[Pico AI Server and Pico AI Studio @PicoGPT]

Apple Silicon + Gemma 4 fans: this is for you.

Pico AI Server now supports continuous batching with MLX-Swift.

43 tok/s on 1 stream.
26 tok/s per stream on 2 concurrent streams.

That’s 52 tok/s total. a 21% throughput gain on a six-year-old MacBook Pro M1 Max!

[Pico AI Server and Pico AI Studio @PicoGPT]

Download today: https://t.co/PQkCSDv6CY

[Pico AI Server and Pico AI Studio @PicoGPT]

Apple Silicon + Gemma 4 fans: this is for you.

Pico AI Server now supports continuous batching with MLX-Swift.

43 tok/s on 1 stream.
26 tok/s per stream on 2 concurrent streams.

That’s 52 tok/s total. a 21% throughput gain on a six-year-old MacBook Pro M1 Max!

[Pico AI Server and Pico AI Studio @PicoGPT]

Oops. Did I say M2.5? I meant M2.7!

[Pico AI Server and Pico AI Studio @PicoGPT]

Pico update: @minimax_ai M2.5 is now available on Apple Silicon Macs with 192GB or more unified memory

[Pico AI Server and Pico AI Studio @PicoGPT]

Free download: https://t.co/PQkCSDv6CY

[Pico AI Server and Pico AI Studio @PicoGPT]

Free download: https://t.co/PQkCSDv6CY

[Pico AI Server and Pico AI Studio @PicoGPT]

Now available on Pico AI Server: Google Gemma 4