Ade Risidore

Building something

[Ade Risidore @aderiz]

https://t.co/TRWPUXpWbw

[Ade Risidore @aderiz]

@agent_cmux is my new favorite terminal. Top work and goodbye terminal screen bloat

[Ade Risidore @aderiz]

@ivanfioravanti @filipstrand @ostrisai Just downloaded and merged @osteris version with my local version. Problem solved :)

[Ade Risidore @aderiz]

I tweaked my own version of @ostrisai ai-toolkit this morning to include it for training testing, but im getting a lot of burned in sensitivity filters even with the json prompts for even the most basic of images - the standard sample set.

Will be monitoring to see how the issue progresses.

Mind you I didn't do mflux... Maybe I'll try that.

[Prince Canuma @Prince_Canuma]

Today we're shipping our biggest MLX-VLM release yet: v0.6.0

...and we are raising 💸

This one's about turning your Apple devices into real local agent machines. From your desk to your pocket.

What's new:

⚡ Speculative decoding everywhere — Gemma 4 EAGLE3 + DFlash, Qwen MTP, DeepSeek V4 MTP. Faster tokens, less waiting.

🤖 Agent-ready server — native Anthropic /v1/messages API, stateful /v1/responses, tool calls, Codex context budgets. Plug Claude Code & Codex straight into local models.

👁️ New models galore — DeepSeek V4, ZAYA1-VL, MiniCPM-V 4.6, LFM2 MoE, Step-3.7 Flash, Laguna + more.

🎨 Image gen & editing — FLUX.2 (base + klein), PrismML Bonsai.

🔊 Audio in — Qwen3 Omni, Gemma 4 audio, base64 chat audio.

🧮 TurboQuant KV cache — RHT-correct fast paths for leaner memory.

📦 Modular server, better metrics, cleaner streaming.

Run real agents on the hardware already in your hands.

Github: https://t.co/1T06ur6LU5

[Ade Risidore @aderiz]

@ivanfioravanti if you're interested in my progress :)

[Ade Risidore @aderiz]

https://t.co/TRWPUXpWbw

[Ade Risidore @aderiz]

huge thanks to @jtdavies for ongoing encouragement, @Prince_Canuma for everything MLX and @pollenrobotics for creating this pocket sized bot for the community to experiment with

[Ade Risidore @aderiz]

@Prince_Canuma No way man, sorry to hear this. Please let us know if we can help in any way

[Ade Risidore @aderiz]

@Prince_Canuma @zohaibahmed @resembleai 🫡

[Ade Risidore @aderiz]

@ivanfioravanti @pollenrobotics @huggingface As promised.

Early days but hopefully something you can steal or at least give you something to think about

https://t.co/8NlPztaxFV

[Ade Risidore @aderiz]

@ivanfioravanti @pollenrobotics @huggingface One slightly aesthetic thing was the 3D animation it’s not readily available but I found a way :)

[Liu Liu @liuliu]

M4 is faster (since a few days ago): https://t.co/PhsF7BQgeS

[Ade Risidore @aderiz]

@Prince_Canuma All good my man, you're entitled to them too (you should see mine hahahahahahah)

Keep fighting the good fight

[Ade Risidore @aderiz]

Wow mlx-community/Qwen3.6-35B-A3B-4bit is biggggggg.

Nice work @Prince_Canuma

[Ade Risidore @aderiz]

@Prince_Canuma will now, i saw 90gb and sighed hard hahaha

[Ade Risidore @aderiz]

@Prince_Canuma Now I need to sell my house for an M5 Max to run it haha wont fit on my 96gb m3 max :( boo

[Ostris @ostrisai]

I trained an ACEStep 1.5 XL LoRA on "some obscure 60s English rock band". Then I wrote a song about LoRA training and had them play it. Absolutely wonderful experience. I still have some UI work before I can make training public in AI Toolkit, but working on it as fast as I can.