busfahrer

I use this solution for your exact use case:

I have a single command that fires up llama.cpp on cpu only using gemma4 e2b, answers a single question from the command line and exits. This takes about 3 seconds to load from an SSD, and is smart enough to solve exactly these "remind me of the syntax" scenarios if you dont wanna switch to a browser.

I use ROT13 twice for extra security

Can confirm, it's very much Hiro Protagonist. I love the style, and the over-the-topness of it all made more sense once I learned that it was originally planned as a graphic novel, IIRC.

Gibson's style is much more post-modern. I read Neuromancer right after Gravity's Rainbow and expected some reprieve from dense prose, but it was almost the same difficulty level, especially for a non-native reader.

edit: Adding my favorite Snow Crash quote:

> When it gets down to it — talking trade balances here — once we've brain-drained all our technology into other countries, once things have evened out, they're making cars in Bolivia and microwave ovens in Tadzhikistan and selling them here — once our edge in natural resources has been made irrelevant by giant Hong Kong ships and dirigibles that can ship North Dakota all the way to New Zealand for a nickel — once the Invisible Hand has taken away all those historical inequities and smeared them out into a broad global layer of what a Pakistani brickmaker would consider to be prosperity — y'know what? There's only four things we do better than anyone else:

> music

> movies

> microcode (software)

> high-speed pizza delivery

> The future is here, it's just not evenly distributed.

One of my favourite Gibson quotes.

I am eyeing one of these specifically for this use case, could you please post roughly what kind of tokens per second numbers you get for text generation for this 27B model?

edit: and which quant you are using, please :-)

Fun fact: The pattern of the torches' flickering is encoded via special strings in the source code:

https://jasemagee.com/post/2022-03-27-26-year-old-quake-ligh...

For anyone who enjoys this sort of thing, I found this postmortem of an Alone in the Dark clone for PICO-8 highly informative:

https://www.lexaloffle.com/bbs/?tid=3804

has anyone been able to get bonsai models to run at a proper speed in a x86 windows cpu-only setting, using llama.cpp?

For anybody else trying to grok backprop, I found it very helpful to look at karpathy's microgpt, a barebones LLM in 200 lines of python. The autograd itself is just 40 lines, and reading that code and then trying to do a clean room implementation of it is a great exercise:

https://gist.github.com/karpathy/8627fe009c40f57531cb1836010...

https://karpathy.github.io/2026/02/12/microgpt/

As a kid I played Ken's Labyrinth, a raycaster FPS from around the same time as Wolf3D. Only years later I found out that this was actually the same Ken Silverman that went on to create the Build engine for Duke Nukem 3D etc. Kind of funny considering the vast difference in tone between these two games.

edit:

https://en.wikipedia.org/wiki/Ken%27s_Labyrinth

I'm on the fence because I have a TSC-X controller and it's unclear if it's supported. Somebody on the forums posted a tool that converts generic joystick axes to keypresses, but not sure how well that works.

> Or maybe Lisp is so pure that it embodies both Light Side and Dark Side, like a god that spawned the programming universe.

This isn't so far off, considering that some people consider the "Lisp in Lisp" bit from the 1.5 manual to be the "Maxwell's Equations in Software":

https://michaelnielsen.org/ddi/lisp-as-the-maxwells-equation...

The PS1 architecture is fascinating - it will also reveal why PS1 games have such a unique, recognizable style that games are trying to recreate nowadays.

To add some context, the author of this article is a science fiction writer, one of his stories was adapted into the movie "Arrival".

Not a one-liner, but I was impressed by this simple rogue-like written in 10 lines of BASIC:

https://bunsen.itch.io/the-snake-temple-by-rax

Having only dabbled in Lisp and knowing nothing about the plugins TFA mentions, there's also this FWIW:

https://github.com/jpalardy/vim-slime

Thank you, good sir!

Great, thanks! :-) and to mirror another poster: what kind of prompt parsing (prefill) speed do you get for that model? Also how is the speed for the 27B model?

I have been contemplating a M5 Pro MBP, but for the life for me I wasn't able to find benchmarks for real-world models, do you happen to know how many tokens per second roughly you get with MoE models like Qwen 3.6 35B/A3B or Gemma 4 26B?

Seeing as this is HN, I was expecting something on chemical properties of iron etc, but was pleasantly surprised

OTOH, with the IMSAI-8080 you'd have the satisfaction of using the same machine as David Lightman of Wargames fame

To add some context, this was made for the PICO-8 fantasy console, which (by design) is very limited, so it's immensely impressive to see something like this working on it. Honestly, even just the 3D logo from the intro is impressive, and the rest of the game even moreso.

https://www.lexaloffle.com/pico-8.php

So I'm guessing it's sort of like Fennel, which consciously doesn't completely hide its underlying Lua runtime?

https://fennel-lang.org/

I am considering a M5 Pro (18/20C) Macbook with 64GB of RAM, but I'm having a really hard time finding benchmarks of real world models:

Could somebody please provide some tokens-per-second numbers for example for Qwen 3.6 35B/A3B, specifically for Q4 and Q6 quants?

This is the whole point of Karpathy's nanochat which OP refers to, to train a GPT-2 level LLM for under $100, renting an 8xH100 VM.

This kind of is Postel's law, in a way:

https://en.wikipedia.org/wiki/Robustness_principle

Out of curiosity, what size Qwen did you use, at what quantization?

I think I remember a Carmack tweet where he mentioned in most cases he only considers it once he reaches three duplicates

This seems like a nice context to mention Sturgeon's law:

> ninety percent of everything is crud

https://en.wikipedia.org/wiki/Sturgeon%27s_law

> Low cost specialized models

Can you elaborate on this? Is this something that companies would train themselves?