Zipslicer, a library for loading LLM checkpoints on consumer hardware
This is a low-level opensource library I developed for my own use and decided to share, as it makes it possible to process large checkpoints of neural networks without renting high-RAM instances, on a regular PC. It replaces torch.load() with a custom function that produces a dictionary that materializes tensors on the fly. Compared to other solutions it doesn't require sharding or re-encoding checkpoints and uses them completely as-is. It is a foundation to make it possible to run inference and compress language models and other large models one layer at a time - in principle, even one…
Zipslicer, a library for loading LLM checkpoints on consumer hardware launched on March 3, 2023 with 38 votes, #1,678 of 5,007 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 3 years on.
In plain words
Zipslicer is an open-source library that enables users to load large neural network checkpoints on consumer computers without renting high-RAM cloud instances. It replaces PyTorch's standard load function with a custom one that materializes tensors on demand from checkpoint files. Unlike alternative solutions, Zipslicer works with unmodified checkpoints and requires no sharding or re-encoding. It allows processing large language models layer-by-layer or even tensor-by-tensor, supporting inference and compression tasks on standard PCs.
written from the facts on this page · September 2026
From the sources
A library for incremental loading of large PyTorch checkpoints - kir-gadjello/zipslicer
In the maker’s words, at launch
This is a low-level opensource library I developed for my own use and decided to share, as it makes it possible to process large checkpoints of neural networks without renting high-RAM instances, on a regular PC. It replaces torch.load() with a custom function that produces a dictionary that materializes tensors on…
Does a similar job
all alternatives →
I built a tiny LLM to demystify how language models workApr 2026 · github.com · ▲915Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
TensorZero2025 · github.com · ▲307Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation:…
Thinc, a new deep learning library by the makers of spaCy and FastAPI2020 · thinc.ai · ▲250Thinc is a lightweight type-checked deep learning library for composing models, with support for layers defined in frameworks like PyTorch and TensorFlow.
LeanRL: Fast PyTorch RL with Torch.compile and CUDA Graphs2024 · github.com · ▲53We're excited to announce that we've open-sourced LeanRL, a lightweight PyTorch reinforcement learning library that provides recipes for fast RL training using torch.compile and CUDA graphs. By leveraging these tools, we've achieved significant speed-ups compared to the original CleanRL implementations - up to 6x faster! Reinforcement learning is notoriously CPU-bound due to the high frequency of small CPU operations. PyTorch's powerful compiler can help alleviate these issues, but comes with its own costs. LeanRL addresses this challenge by providing simple recipes to accelerate your…
CodeRLM – Tree-sitter-backed code indexing for LLM agentsFeb 2026 · github.com · ▲81I've been building a tool that changes how LLM coding agents explore codebases, and I wanted to share it along with some early observations. Typically claude code globs directories, greps for patterns, and reads files with minimal guidance. It works in kind of the same way you'd learn to navigate a city by walking every street. You'll eventually build a mental map, but claude never does - at least not any that persists across different contexts. The Recursive Language Models paper from Zhang, Kraska, and Khattab at MIT CSAIL introduced a cleaner framing. Instead of cramming everything into…
I created a RAW to HDRI stacker in (mostly) Common LispJun 2026 · github.com · ▲35This is an upgrade of a tool I created 15 years ago in Python to learn OOP and solve some inadequacies in the HDR stacking tools I could find at the time. The problem was, none of them were really "batch friendly". None of them properly preserved the metadata I wanted them to stuff into the output file. There were probably some other reasons also, I just can't remember them now. It got the job done, but was very slow. Python was what I knew at the time and even with NumPy, I was limited in the speed I could squeeze out of it. (I also made some very specific, conscious, architectural choices…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2023
the whole month →
Typing Mind▲826Chat with AI using your API keys. Pay only for what you use. ChatGPT, Gemini, Claude, and other LLMs supported. The best chat LLM frontend UI for all AI models.
AI · 2023 · typingmind.com
Sequoia▲726Personalized men's sexual health with on-demand experts
Life & fun · 2023 · sequoia.health
- BI
I'm a big fan of the BBC podcast In Our Time -- and (like most people) I've been playing with the OpenAI APIs. In Our Time has almost 1,000 episodes on everything from Cleopatra to the evolution of teeth to plasma physics, all still available, so it's my starting point to learn about most topics. But it's not well organised. So here are the episodes sorted by library code. It's fun to explore. Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript definition. At the same time I…
AI · 2023 · genmon.github.io