With all the different open-weight models appearing, is there some way of figuring out what model would work with sensible speed (> X tok/s) on a standard desktop GPU ? I.e. I have Quadro RTX 4000 with 8G vram and seeing all the models https://ollama.com/search here with all the different sizes, I am absolutely at loss which models with which sizes would be fast enough. I.e. there is no point of me downloading the la…
8G VRAM for LLM, are you sure? I thought you need way more, 20GB++
Nvidia doesn't want peasants running own LLMs locally, 90% of their business is supporting AI bubble with a lot of GPU datacenters
I find the situation the big LLM players find themselves in quite ironic. Sam Altman promised (edit: under duress, from a twitter poll gone wrong) to release an open source model at the level of o3-mini to catch up to the perceived OSS supremacy of Deepseek/Qwen. Now Qwen3’s release makes a model that’s “only” equivalent to o3-mini effectively dead on arrival, both socially and economically.
OAI in general seems to be treading water at best. Still topping a lot of leaderboards but severely reduced rep. Chaotic naming, „ClosedAI“ image, undercut on pricing, competitors with much better licensing/open weights, stargate talk about Europe, Claude being seen as superior for coding etc. nothing end of the world but a lot of lukewarm misses If I was an investor with financials that basically require magical ret…
OpenAI has the business development side entirely fleshed out and that’s not nothing. They’ve done a lot of turns tuning models for things their customers use.
If OpenAI's flagship model can't add a simple calendar event, that doesn't do much to assuage my disappointment...
I remember vividly that the focus on GPT-4.1 to speak more humane and be more philosophical when speaking. I remember something like that. That model is special and is not meant like a next generation of their other models like 4o and o3.
I'm not sure if it's just me hallucinating , but it seems like with every new model release, it suddenly tops all the benchmark charts—sometimes leaving the competition in the dust. Of course, only real-world testing by actual users across diverse tasks can truly reveal a model’s performance. That said, I still find a sense of excitement and hope for the future of AI every time a new open-source model is released.
Yeah, but their comparison tables appear a bit skewed. o3 doesn't feature, nor does Claude 3.7
I have a small physics-based problem I pose to LLMs. It's tricky for humans as well, and all LLMs I've tried (GPT o3, Claude 3.7, Gemini 2.5 Pro) fail to answer correctly. If I ask them to explain their answer, they do get it eventually, but none get it right the first time. Qwen3 with max thinking got it even more wrong than the rest, for what it's worth.
My favorite test is "Build an MTG Arena Deck in historic format around in . It must be exactly 60 cards and all cards must be from Arena only. Search all sets/cards currently availble on Arena, new and old".
Many times they’ll include cards that are only available in paper and/or go over the limit, and when asked to correct a mistake they'll continue to make mistakes. But recently I found that Claude is pretty damn good now at fixing its mistakes and building/optimizing decks for Arena. Asked it to make a deck based on insights it gained from my current decklist, and what it came up with was interesting and pretty fun to play.
Personally (anecdata) I haven't experienced any practical progress in my day-to-day tasks for a long time, no matter how good they became at gaming the benchmarks. They keep being impressive at what they're good at (aggregating sources to solve a very well known problem) and terrible at what they're bad at (actually thinking through novel problems or old problems with few sources). E.g. all ChatGPT, Claude and Gemini…
Absolutely. All models ar terrible with Objective-C and Swift, compared to let's say JS/HTML/Python. However, I've realized that Claude Code is extremely useful for generating somewhat simple landing pages for some of my projects. It spits out static html+js which is easy to host, with somewhat good looking design. The code isn't the best and to some extent isn't maintainable by a human at all, but it gets the job do…
Personally (anecdata) I haven't experienced any practical progress in my day-to-day tasks for a long time, no matter how good they became at gaming the benchmarks. They keep being impressive at what they're good at (aggregating sources to solve a very well known problem) and terrible at what they're bad at (actually thinking through novel problems or old problems with few sources). E.g. all ChatGPT, Claude and Gemini…
Absolutely. All models ar terrible with Objective-C and Swift, compared to let's say JS/HTML/Python. However, I've realized that Claude Code is extremely useful for generating somewhat simple landing pages for some of my projects. It spits out static html+js which is easy to host, with somewhat good looking design. The code isn't the best and to some extent isn't maintainable by a human at all, but it gets the job do…
I’ve gotten 0 production usable python out of any LLM. Small script to do something trivial, sure. Anything I’m going to have to maintain or debug in the future, not even close. I think there is a _lot_ of terrible python code out there training LLMs, so being a more popular language is not helpful. This era is making transparent how low standards really are.
I'm curious what kind of prompting or context you are providing before asking for a liquid soap script - or if you've tried using Cursor and providing a bunch of context with documentation about liquid soap as part of it. My guess was these kinds of things get the models to perform much better. I have seen this work with internal APIs / best practices / patterns.
Yes, I used Cursor and tried providing both the whole Liquidsoap book or the URL to the online reference just in case the book was too large for context or it was triggering some sort of RAG. Not successful. It's not that it didn't do what I wanted: most of the time it didn't even run. Iterating on the error messages just arrived at progressively dumber not-solutions and running in circles.
I have a small physics-based problem I pose to LLMs. It's tricky for humans as well, and all LLMs I've tried (GPT o3, Claude 3.7, Gemini 2.5 Pro) fail to answer correctly. If I ask them to explain their answer, they do get it eventually, but none get it right the first time. Qwen3 with max thinking got it even more wrong than the rest, for what it's worth.
I similarly have a small, simple spatial reasoning problem that only reasoning models get right, and not all of them, and which Qwen3 on max reasoning still gets wrong. > I put a coin in a cup and slam it upside-down on a glass table. I can't see the coin because the cup is over it. I slide a mirror under the table and see heads. What will I see if I take the cup (and the mirror) away?
My favorite part of the genre of “questions an LLM still can’t answer because they’re useless!” is all the people sharing results from different LLMs where they clearly answer the question correctly.