Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
| From | Mild Shock <janburse@fastmail.fm> |
|---|---|
| Newsgroups | sci.math, sci.logic, sci.physics.relativity |
| Subject | Cute Racoon generated with Local AI (Was: The joy of running an AI Model on your AI Laptop [Local AI]) |
| Date | 2025-11-11 23:26 +0100 |
| Message-ID | <10f0d5s$5bbb$1@solani.org> (permalink) |
| References | <10bs8fq$hne8$3@solani.org> <10bs98j$hnv4$3@solani.org> <10bsa17$hob3$3@solani.org> <10esugq$32sm$1@solani.org> <10f05bu$afg7$2@solani.org> |
Cross-posted to 3 groups.
Hi, There is even more joy of running an AI Model on your AI Laptop. All you need to put "AI Slob" into the wild is Stable Diffusion Software and Models. Cute Racoon generated with Local AI https://www.youtube.com/shorts/QlS0MqMh_bM Have Fun! Bye P.S.: Was using this gadget: Create AI art, with the latest Stable Diffusion models, on your own PC. https://www.amuse-ai.com/ Mild Shock schrieb: > Hi, > > Now that was a little unexpected that Intel beats AMD. > Could get my hands on two AI Laptops for testing. > The have both DDR5X Ram. > > AI Laptop 1: Acer_Swift_SFG16-61 > AMD Ryzen 7 350 > Radeon Graphics > AMD Ryzen AI Boost, up to 50 TOPS > > AI Laptop 2: LENOVO_83JQ > Intel Core Ultra 7 258V > Intel Arc Graphics 140V > Intel AI Boost, up to 47 TOPS > > I couldn't test the AI Boost yet. Besides the nice > CPUs, the iGPU and the fast memory, in this case > 32 GB, seem to give quite some bang: > > Here some test with LMStudio, I picked the > model Qwen3 Coder 30B, with Q4_K_M encoding, > which is around 16 GB, and fits into my GPU memory: > https://lmstudio.ai/models/qwen/qwen3-coder-30b > > AI Laptop 1: 18 Tokens/s > > AI Laptop 2: 6 Tokens/s > > Now I am waiting for drivers and applications > that make use of the AI Boost. Will say > I only tested the iGPU, not yet the NPU. > > For the donwload of the AI model it is > required to have fiber and WiFi 6, you can > then make it in less than a minute, even > > if you are far away from the router. > > Bye > > P.S.: The 18 Tokens/s are quite fluid, > the 6 Tokens/s are a little annoying. But > on both machines I could converse with the > > model, and go from primes to twin primes. > It didn't use any RAG, fully produce via > Local AI, also no remote AI access after > > download of the AI Model: > > ----------------- cut here --------------------- > > Here's a Prolog implementation to find > twin prime pairs (pairs of primes that differ by 2): > > % Generate twin prime pairs up to N > twin_primes_up_to(N, TwinPairs) :- > findall((P, Q), > (between(3, N, P), > is_prime(P), > Q is P + 2, > is_prime(Q)), > TwinPairs). > > % Check if a number is prime > is_prime(2) :- !. > is_prime(3) :- !. > is_prime(N) :- > N > 3, > N mod 2 =\= 0, % Even numbers > 2 are not prime > \+ has_factor(N, 3). % Check if N has any factors starting from 3 > > % Check if N has a factor starting from F > has_factor(N, F) :- > F * F =< N, > (N mod F =:= 0 ; has_factor(N, F + 2)). > > Example usage: > > ?- twin_primes_up_to(20, Pairs). > Pairs = [(3, 5), (5, 7), (11, 13), (17, 19)]. > > ?- twin_primes_up_to(50, Pairs). > Pairs = [(3, 5), (5, 7), (11, 13), (17, 19), (29, 31), (41, 43)]. > > This finds pairs of primes (P, Q) where Q = P + 2, > which are called twin primes. The findall/3 predicate > collects all such pairs where both P and P+2 are > prime numbers and P is less than or equal to N. > > ----------------- cut here ---------------------
Back to sci.math | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
Vanishing Point . [Le Dot] Mild Shock <janburse@fastmail.fm> - 2025-10-05 00:52 +0200
Lets compare AI data centers (Re: Vanishing Point . [Le Dot]) Mild Shock <janburse@fastmail.fm> - 2025-10-05 01:05 +0200
USA domestic chips for the never ending crunch (Re: Lets compare AI data centers) Mild Shock <janburse@fastmail.fm> - 2025-10-05 01:19 +0200
OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch) Mild Shock <janburse@fastmail.fm> - 2025-11-10 15:57 +0100
Re: OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch) olcott <polcott333@gmail.com> - 2025-11-10 12:20 -0600
Re: OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch) "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2025-11-10 12:08 -0800
Re: OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-11-10 17:05 -0800
The joy of running an AI Model on your AI Laptop [Local AI] (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem]) Mild Shock <janburse@fastmail.fm> - 2025-11-11 21:09 +0100
The joy of running an AI Model on your AI Laptop [Local AI] (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem]) Mild Shock <janburse@fastmail.fm> - 2025-11-11 21:12 +0100
Cute Racoon generated with Local AI (Was: The joy of running an AI Model on your AI Laptop [Local AI]) Mild Shock <janburse@fastmail.fm> - 2025-11-11 23:26 +0100
Meta is Dust: Yann LeCun crushed by Behemoth China (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem]) Mild Shock <janburse@fastmail.fm> - 2025-11-13 19:03 +0100
Even Prolog now depends on China (Was: Meta is Dust: Yann LeCun crushed by Behemoth China) Mild Shock <janburse@fastmail.fm> - 2025-11-13 19:13 +0100
Re: Even Prolog now depends on China (Was: Meta is Dust: Yann LeCun crushed by Behemoth China) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-11-13 11:42 -0800
Re: Vanishing Point . [Le Dot] Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-10-04 18:38 -0700
Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0). (Was: Vanishing Point . [Le Dot]) Mild Shock <janburse@fastmail.fm> - 2025-10-05 10:09 +0200
Holy Schrimp Jesus: The Internet is Dead [Rossy Boy dethroned?] (Was: Creative Commons Attribution-ShareAlike 4.0 International License) Mild Shock <janburse@fastmail.fm> - 2025-10-05 10:29 +0200
Re: Holy Schrimp Jesus: The Internet is Dead [Rossy Boy dethroned?] (Was: Creative Commons Attribution-ShareAlike 4.0 International License) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-10-05 10:29 -0700
Re: Holy Schrimp Jesus: The Internet is Dead [Rossy Boy dethroned?] (Was: Creative Commons Attribution-ShareAlike 4.0 International License) kinak <kin@mob.net.inv> - 2025-10-05 18:57 +0100
Re: Holy Schrimp Jesus: The Internet is Dead [Rossy Boy dethroned?] (Was: Creative Commons Attribution-ShareAlike 4.0 International License) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-10-05 11:06 -0700
British writer Arthur C. Clarke (Re: Vanishing Point . [Le Dot]) Mild Shock <janburse@fastmail.fm> - 2025-10-05 19:33 +0200
Aryabhatta of Bihar [Indian Mathematician-Astronomer] (Re: British writer Arthur C. Clarke) Mild Shock <janburse@fastmail.fm> - 2025-10-05 19:34 +0200
Re: British writer Arthur C. Clarke (Re: Vanishing Point . [Le Dot]) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-10-05 11:06 -0700
Knight Rider (2025/2026) will kill us all (Was: Vanishing Point . [Le Dot]) Mild Shock <janburse@fastmail.fm> - 2025-11-13 21:52 +0100
The AGI Gambit: Hype vs. Reality (Re: Knight Rider (2025/2026) will kill us all) Mild Shock <janburse@fastmail.fm> - 2025-11-13 21:59 +0100
Stable Diffusion with Control Net (Re: The AGI Gambit: Hype vs. Reality) Mild Shock <janburse@fastmail.fm> - 2025-11-13 23:04 +0100
csiph-web