Best bet and investment I’ve ever made in myself This was a crazy stupid thing to do back in 2023/2024 but I fully believed Local and Opensource AI were the future
OPEN SOURCE
-
Ollama slower, slop, code thieves; better alternatives listed
By
–
ollama > slower than llama.cpp on windows
> slower than mlx on mac
> slop useless wrapper
> literal code thieves alternatives? > lmstudio
> llama.cpp
> exllamav2/v3
> vllm
> sglang
> trt-llm literally anythingʼs better than ollama -
Why focus on inference engines: performance gains with vLLM and Sglang
By
–
Why do I focus on Inference Engines/Software Stacks for your hardware? – 2x RTX 3090s: ~14.5 tok/s → ~64 tok/s moving to vLLM w/ TP=2 – RTX PRO 6000: ~32 tok/s → ~110 tok/s moving to Sglang So: – CUDA/2+ GPUs: ExLlamaV3/vLLM/Sglang > llama.cpp – Edge: llama.cpp > Ollama
-
Equivalent SOTA model, open access, not free, no third-party dependency
By
–
In fact, you have a model equivalent to SOTA models on many benchmarks, freely accessible, obviously not free because you have to account for the cost of hardware, but thus possibly without depending on a third-party actor. What is good when a new model comes out is to look at
-
Popularizing open-weights versus labs’ open source
By
–
No, on the contrary, it's called popularizing. The term open-weights is very restrictive today. Especially when the labs themselves talk about open source.
-
The expression ‘open weight’ is not understood by everyone
By
–
If I say open weight, nobody will understand.
-
AI Domination: Open-source then General, and What’s Next?
By
–
– 2016-2024: dominates open-source AI
– 2024-2027: dominates general AI and benefits massively from it – 2024-2026: dominates open-source AI
– 2026-2030: ?? It is not the domination of open-source AI OR the domination of general AI, it is the domination of AI -
Turn any paper into running code with autoarxiv
By
–
Turn any paper into running code.
— Akshay 🚀 (@akshay_pachaar) 21 juin 2026
Just swap arxiv → autoarxiv in the paper url.
That hands the paper to an AI agent from alphaXiv. It reads the abstract, the claims, and the linked GitHub repo, then clones the codebase and works through the usual setup pain like dependencies,… pic.twitter.com/UOPJnWdfLJTurn any paper into running code. Just swap arxiv → autoarxiv in the paper url. That hands the paper to an AI agent from alphaXiv. It reads the abstract, the claims, and the linked GitHub repo, then clones the codebase and works through the usual setup pain like dependencies,
-
Vercel CEO impressed by GLM-5.2, open source and open weights
By
–
Even the CEO of Vercel is impressed/shocked by the exceptional performance of GLM-5.2 in coding. open source, open weights.