AMJ

#TecAddict
#Motard tôt le matin aussi
OTP Ekko Emerald #LeagueofLegends

[AMJ @Aemji_]

it's live and available #heracles https://t.co/UwCkEIksty

[AppleGeek @Apple_Geek_Actu]

✨🚨 Apple annonce un jour nouveau. Bientôt.

Rendez-vous le 9 septembre à 19h pour suivre la keynote en direct.

[AMJ @Aemji_]

@ashxhart How about offload engram on ssd ?

[AMJ @Aemji_]

@UnslothAI Hello, what is the weight in GB of the Engram part ?

[Alexey Fateev @superalesha]

I've already started rewriting llama.cpp for the 51B N-grams that will be in Qwen3.8 Flash Next.

In Qwen3.8 Flash Next they are stored in a separate N-gram table, and I want to achieve one thing - offload exactly that table to RAM. The GPU will only access it for the current token.

Sounds simple? Not at all.

There are several implementation options:
1. Slow
2. Quality might get worse
3. Quantization is a whole separate problem that I won't talk about yet.

Maybe Qwen will release support for this right away. And if not - I'll do it myself.

To be continued when the weights are out.

[TheDavidTai @TheDavidTai]

Model Size Breakdown:

RAM:
- Q4 routed experts: 64.60 GiB
- Remaining BF16 model weights: 10.22 GiB
- n-gram look table: < 1 GiB
- Total: about 75.82 GiB

SSD:
- BF16 n-gram table: 95.37 GiB

[Qwen @Alibaba_Qwen]

⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weight!

The production version Qwen3.8-Flash will be available soon via QwenCloud API at just $ 0.16/1M input tokens and $ 0.47/1M output tokens.

125B parameters + 51B N-gram embeddings, with just 6B activated per token. Unmatched cost-efficiency.

What's new: 🥳
- Next architecture: GDN + QSA hybrid attention, Gated Residual, N-gram Embedding & Muon optimizer, serving as a precursor to the architecture used in Qwen4.
- Dramatically lower training and inference costs: trained at just 1/9 the cost of Qwen3.7-Plus, while outperforming it across the board with especially strong gains in coding and office tasks.
- Strong performance: scoring 58.7 on DeepSWE 1.1, 62.5 on SWE-bench Pro, 73.9 on CoWorkBench, 84.5 on AndroidWorld, and 95.7 on MathVision (with CI).
- 262K native context, extensible to 1M with YaRN.

We’re also releasing the weights for Qwen3.8-Flash-Next, giving the community an early look at the new architecture we’re exploring for Qwen4.🚀

We can't wait to see what you build with Qwen3.8-Flash!👀👇
- Blog: https://t.co/M5hYypFLgJ
- Technical Report: https://t.co/IF0gObIkQO
- Hugging Face: https://t.co/6ow8QVAABt
- ModelScope: https://t.co/tDOn2jNuFG

[AMJ @Aemji_]

@magicalchris98 C’est mon Héros, il remet a sa place les gens complaisant d’en haut

[Jun Song @jun_song]

A lot of people who own an M3 Ultra have been DMing me asking if they should sell it.

Short answer: Yes, sell it while you still can.

I actually sold mine not too long ago.

The main reason is the new neural accelerator in the M5 series. It gives you at least 4x faster prefill speeds compared to the older M3 Ultra.

Slow prefill was always the M3 Ultra's biggest weakness. It was the exact reason why it felt slower in real-world use than a DGX Spark, even though the DGX had way lower memory bandwidth. The M5 Ultra finally fixes this.

The real-world performance gap is basically like jumping from an RTX 3090 to a 5090. If you can find a buyer right now, I strongly recommend selling.

[AMJ @Aemji_]

@ModelScope2022 It’s you Qwen-ichi 4.0 ❤️

[AMJ @Aemji_]

C’est le minimum sinon les fondamentaux c’était 0€ et faudrait shorter

[International Cyber Digest @IntCyberDigest]

❗️OpenAI has published the first performance numbers for Jalapeño, its custom inference chip that was designed with the use of AI.

On SemiAnalysis' InferenceX benchmark, OpenAI says the 700W part delivered 1.5–1.9× the throughput per watt and up to 3.6× lower end-to-end latency of Nvidia GB200 and GB300 systems.

Deployment starts inside OpenAI by year end.

[AMJ @Aemji_]

@AstraiaAI I need your help please 🥹 @luoyike2003

[Ronald Mannak @ronaldmannak]

Apple is closing the local AI performance gap with Nvidia fast and is already ahead on cost. And with Apple Upgrade leasing, it’s honestly the best option available. A few trends worth watching:

- Low end: Apple already beats systems like the DGX Spark on both price and performance. Nvidia needs a meaningful Spark upgrade to stay competitive.
- Mid range: Nvidia still leads in prefill and decode, but the gap keeps shrinking with every Apple Silicon generation.
- Total cost: Once you include the machine, power consumption, and other costs, Apple is already be cheaper than mid-range Nvidia
- Power + noise: Apple remains in a different league on efficiency and acoustics, especially important when the machine sits in the same room.
- Financing: Apple’s 0% financing/upgrade options make the economics even more compelling: use the machine for 24 or 36 months, then return it, upgrade it, or pay the remainder to keep it.
I know what I would buy

[AMJ @Aemji_]

You will regreat it

[Scott R. Leimroth @ScottLeimroth]

Apple M5 Ultra. $20,000 No thanks

[AMJ @Aemji_]

Apparently 51B of Qwen 3.8 Flash Next could really be offload on SSD and partially load in RAM when needed : https://t.co/b6iFjjc5aE

[AMJ @Aemji_]

Le Coca et les bières!

[Cadence Agyirey 🇬🇭🏳‍⚧ @kubedoll]

@TheZachMueller The era of expert offloaded engineering has arrived

[AMJ @Aemji_]

La demande est trop grande pour être absorbé, 1er fautif la RAM on est à un stade où les gens cherche à acheter le même niveau de RAM que la capacité de stockage d’un disque dur il y a 5ans on est passé à de la demande de 8-16go à du 64-128-256-512go
Les prix flambent (ça devrait se calmer à terme vu le ratio ram/performance des derniers models de qwen… quoi que on sait pas ce qu’ils vont sortir en Septembre…)

Les Mac Studio actuel devraient être vendu plus cher, vu les prix actuel de la ram partout ailleurs

On est dans une situation de marché où l’IA permet de générer de l’argent même de manière passive, pour moins cher que de l’immobilier SANS les contraintes de l’immobilier

Les prix ont pas fini de monter

[AMJ @Aemji_]

Après une hausse des prix sans sortie de nouveau produit à une date aléatoire pour la PREMIERE FOIS de son histoire.

pour la première fois, Apple fait une annonce de sortie anticipé ET rationne le nombre d'achats, pas plus de 2 exemplaire achetable par personne... si vous avez pas compris ce qu'il se passe, je peux rien pour vous

[AMJ @Aemji_]

🤣

[AMJ @Aemji_]

@magicalchris98 Ah non, une femme ça a des cheveux et sa porte du rose
Un homme ça a pas de cheveux et ça s’habille en bleu

#jesuismatrixé 🤣