Building something
London
Joined March 2009
- Tweets2K
- Following740
- Followers420
- Likes11.3K
Ade Risidore retweeted
We are live on @thursdai_pod with inferd
We wrote an inference engine for running agents, agent-swarms and agentic AI on MacOS.
Finally you can get Nvidia performance from your Apple Mac.
inferd.incept5.ai
1,487 tok/s on Qwen3.8-Flash-Next - Open Source!
Ade Risidore retweeted
Last night, @higgsfield sent @ComfyUI a cease and desist (attached)
They want the Open Source Higgsfield challenge taken down within 48 hours.
Their argument is that our use of the Higgsfield name and that using their CEO's likeness is an infringement violation (man, the irony). Claiming that it makes the event look like Higgsfield is associated with it.
This couldn't be farther from the truth, which is that Higgsfield made a promise to open source its product and never did.
For the past two weeks, builders have been recreating popular closed apps as open workflows anyone can run.
So we asked our community to deliver where Higgsfield failed: apps in the open, built by the community, for the community. We've made it clear that the challenge is organized by ComfyUI and not affiliated with or endorsed by Higgsfield.
When we started Comfy, we made the community a promise. Our product stays open, free, and yours. We’ve kept it every day since, and one letter isn’t going to change that.
The challenge stays up. Comfy and open source will win!
Ade Risidore retweeted
Qwen4, coming soon…
CTO quote was “next week”
Xudong Guo - Research Scientist, Qwen, Token Foundry
Live from Amsterdam
Ade Risidore retweeted
From the @Alibaba_Qwen Cloud CTO, Dr. Feifei Li - “Qwen4 next week”.
Live from Apsara, Amsterdam.
Ade Risidore retweeted
FLUX 3 Image Klein is here.
Open Weights with the quality of a large frontier model. Customizable and fast.
5.6B parameters and runs on a single consumer GPU.
Native 4K, bounding boxes, and pixel-perfect editing.
Ade Risidore retweeted
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: github.com/Blaizzy/mlx-vlm
Ade Risidore retweeted
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.
Ade Risidore retweeted
MLX + TurboQuant = Local Super Power
Take a local (private) document(s) or codebase, pre-fill the 256k KV cache (the context) with the document(s) and system prompt, quantise and run on Apple's MLX and you have almost instantaneous, lossless document queries with total privacy.
For a 75-page PDF (some 30k tokens), I was seeing sub-150ms TTFT (Time To First Token), that's "instant" for a human. We run this on an office server (one of our Mac Minis) for staff to work with, instant answers on critical, confidential company/client documents on phone, iPads or laptops.
Imagine the "What were the 3Q25 profits?", "When did Joe start working for us?", "Please list the project milestones and team count" answered within seconds of hitting the return key. It works with voice too.
This example is 17k lines of code from 177 source files plus an index of the entire 1,902 files, the entire Claude Code codebase (oops Anthropic!). Zero loss (unlike Anthropic's security).
What this means is the ability to work better on local (private) code bases, off-the-shelf private document analysis with better response than the best public models - all locally.
Ade Risidore retweeted
Great fun getting @_Checkit PM and Engineering leadership together at the @mollerinstitute today. Roadmap stuck on the windows, thinking about how to re-design objects like smoke alarms, and entertainment with balloons. Fancy joining in? We’re hiring!
Ade Risidore retweeted
4pm tomorrow!! 💊💊 ⏰
@MrsQuaye @NHSBartsHealth @APTUK1 @WePharmacists #pharmacy #pharmacyhour #healthcare #healthtech #NHS
Ade Risidore retweeted
"If I dig down in search of the root cause of most hiring mistakes, the common denominator is often haste. The organization has a role that needs to be filled yesterday, and the process is rushed."
Ade Risidore retweeted
Fuse Partner and L&D Leader Donna Johnston will be joining Steve Dineen for a live discussion on how to execute an agile L&D strategy that allows learners to thrive. You don't want to miss this! #Learning hubs.ly/H0s7htz0
Ade Risidore retweeted
Only one hour ⏱ to go until our panel joins us live to discuss how L&D are adapting to the realities of the lockdown. If you've not already registered now is the time to join the conversation 👉hubs.ly/H0q0nkP0 #learninganddevelopment #employeeengagement #learningdesign
Ade Risidore retweeted
Today we go live at 4pm with some of the leading minds of L&D to talk practically around how the best teams are tackling COVID-19. It's not too late to register, we'd love you to join us! hubs.ly/H0p-t9J0
Ade Risidore retweeted
Are you free tomorrow at 4pm BST? Join @stevedineen, @siriwikander, Vodafone, Avon and a host of other guests for a live roundtable discussion. They'll be discussing how L&D are adapting to the demands of the COVID-19 lockdown. hubs.ly/H0pZWJV0
#learninganddevelopment
Ade Risidore retweeted
“The task of a teacher is not to work for the pupil nor to oblige him to work, but to show him how to work."
― Wanda Landowska
