Viewing profile — bertili

The 27B have many more active parameters than much bigger models such as DS4Flash, MiniMax etc, which makes it punch above its tiny weight. A great fit for a 5090 in a closet for m…

That looks promising! As models become a commodity, this may turn out to be the real AI gold rush.

Is there any (near future) technology that would permit burning this terrabyte into some kind of ROM chip?

Wait.. the Qwen Max models have never been open-weight. But it sure sound like that's what they intend now? "Qwen3.8 is launching and going open-weight soon! With a massive 2.4T pa…

AGI is almost here, but first, one more thing... a keyboard controller!

Legislators, please require 10 seconds of load screen with a picture of a tree, for every online video. It worked for cigarette packs.

[dead]

This is GLM 5.2 Max. GLM 5.2 High which use less than half[1] the tokens. [1] https://z.ai/blog/glm-5.2

Qwen 27b is a compute heavy dense model.

Does this translate into a similar reduction in compute? What's the catch?

equals 2 or 3 human brains in power usage. Amazing work!

It's fascinating that a $999 Mac Mini (M4 32GB) with almost similar wattage as a human brain gets us this far.

Is there any source for these claims?

A relief to see the Qwen team still publishing open weights, after the kneecapping [1] and departures of Junyang Lin and others [2]! [1] https://news.ycombinator.com/item?id=472467…

The timing is interesting as Apple supposedly will distill google models in the upcoming Siri update [1]. So maybe Gemma is a lower bound on what we can expect baked into iPhones. …

Qwen: Hold my beer https://news.ycombinator.com/item?id=47615002

Very impressive! I wonder if there is a similar path for Linux using system memory instead of SSD? Hell, maybe even a case for the return of some kind of ROMs of weights?

Better than frontier pelicans as of 2025

Most certainly not, but the Unsloth MLX fits 256GB.

Last Chinese new year we would not have predicted a Sonnet 4.5 level model that runs local and fast on a 2026 M5 Max MacBook Pro, but it's now a real possibility.

Exactly. The emperor has no clothes. The largest investments in US tech in history and yet there less than a year of moat. OpenAI or Anthropic will not be able to compete with Chin…

Surely this is the elephant in the room, but the point here is that Apple as control over its ecosystem, so it may be able to sandbox and make entitlements and transparency good en…

People are running the previous Kimi K2 on 2 Mac Studios at 21tokens/s or 4 Macs at 30tokens/s. Its still premature, but not a completely crazy proposition for the near future, giv…

The other realistic setup is $20k, for a small company that needs a private AI for coding or other internal agentic use with two Mac Studios connected over thunderbolt 5 RMDA.

The "Deepseek moment" is just one year ago today! Coincidence or not, let's just marvel for a second over this amount of magic/technology that's being given away for free... and ho…