Alternatives
Products that do what ChonkLM – Tiny language models running offline in the browser does
I had been looking to try <500M parameter language models but you wouldn't find an API to try them anywhere, so I built this cloudflare hosted static website that hosts weights and built an inference runtime for these models that uses WebGPU and runs inference from your browser. These are only so useful in a multi-turn conversation but it's still interesting to see what you can pack in a <250mb model. I tried using ONNX versions earlier, but there were too many quirks of using them with language models and the TPS wasn't too impressive. Inspired by svenflow/webgpu-gemma, I put my codex…
- 1GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
Jul 2026 · github.com
- 2OS
Hi HN, I built a specialized inference engine for running 4-bit Gemma 4 26B-A4B-IT on any M-series Mac using about 2 GB of RAM. It is called TurboFieldfare and is written in Swift and Metal. I have always adored on-device AI. It feels like magic that you can run a powerful NN on your Mac or iPhone. So I wanted to push the limits a bit and run a model whose weights don’t fit in memory. The model’s 4-bit quantized weights occupy roughly 14 GB, which makes running it with conventional inference tools almost impossible on an 8 GB or even 16 GB Mac once the OS, applications, and KV cache are…
Jul 2026 · github.com
- 3FT
Aug 2026 · github.com
- 4
- 5
- 6NG
Hi everyone, I started working on nanoeuler after the ban of anthropic's fable because my ambition and dream is to work in the AI field in anthropic. The two interesting reasons that led me to create nanoeuler were (1) interfacing with llm does not mean understanding how they are composed and (2), working on llm with a very low-level layer to understand the correlation between parameters and data and growth of the model and how the GPU works and how some layers can be optimized. So I started working on it with a research aspect by making nanoeuler grow more and more but doing one step after…
Jun 2026 · github.com
- 7
- 8
- 9AT
A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.
27d ago · mikeayles.com
- 10ML
Aug 2026 · github.com
- 11RR
runNburn is an Apache-2.0 Rust inference engine for quantized GGUF models that are too big for your fast memory. The core idea: weights stay file-backed (mmap), host residency stays under an explicit byte budget (--ram-budget), and GPU caches are sized from detected free/total VRAM — never from device-name presets. There is no conversion step, no sidecar cache files, no silent requantization. The GGUF on disk is the single source of truth. The result that made me want to post this: Tencent's Hy3 (295B total / 21B active sparse MoE, a single 97.8 GiB Q2_K GGUF) runs on my desktop…
Jul 2026 · github.com
- 12
High performance storage engine for efficient LLM inference and GPU Training.
15h ago · theopenlake.com
- 13LT
Hi HN! I'm the author of mere.run a local first inference runtime built around an installable CLI. I believe that whenever possible we should use the stuff we already own (like our Mac laptops, decent machines gathering dust, our gaming PC) and the limited electrical power we have easy access to, like the socket in the wall next to most of us. We shouldn't have to send our data to the cloud hoping some T&C will prevent it from being used in a way that we'd regret. Most of the local AI solutions are technical, involved, and land a curious body in some package hell. People are optimizing for…
Jul 2026 · github.com
- 14RG
I wanted to know how fast a 26B mixture-of-experts model could run on a desktop CPU with no GPU. Got ~40 tok/s single-stream (lossless) and ~124 batched. The surprising part was the byte budget: for this model you compress the output head (32% of per-token bytes), not the experts (16%). The writeup has the bandwidth roofline and the dead-ends; the repo has the reproducible recipe. Happy to answer questions. Repo: https://github.com/arun-prasath2005/gemma4-cpu-moe
Jun 2026 · apeg.dev
- 15MA
I've been working on training this small vision language model for the last month - excited to release the first prototype today! It is based on SigLIP (image encoder), Phi-1.5 (text model) and trained using the LLaVa-1.5 training dataset. It runs reasonably fast on CPU with ~8GB of RAM in full 32-bit precision. There's plenty of room to speed it up and reduce memory consumption by quantizing the model. I posted a video of it running on my M2 Macbook Air (on CPU not MPS, so performance should be comparable on other hardware) on Twitter to demonstrate inference speed:…
2023 · github.com
- 16MM
Hi HN! We (Thomas and Stéphan, hello!) recently released Model2Vec, a Python library for distilling any sentence transformer into a small set of static embeddings. This makes inference with such a model up to 500x faster, and reduces model size by a factor of 15 (7.5M params or 15/30MB on disk, depending on whether you use float16 or float32). This allows you to embed 50-100k documents per second on a cpu on a macbook. This reduction of course comes at a cost: distilled models are worse than their parent models. Even so, they are actually a lot better than large sets of conventional…
2024 · github.com
- 17S1
I wanted to build an inference provider for proprietary AI models, but I did not have a huge GPU farm. I started experimenting with Serverless AI inference, but found out that coldstarts were huge. I went deep into the research and put together an engine that loads large models from SSD to VRAM up to ten times faster than alternatives. It works with vLLM, and transformers, and more coming soon. With this project you can hot-swap entire large models (32B) on demand. Its great for: Serverless AI Inference Robotics On Prem deployments Local Agents And Its open source. Let me know if anyone…
Nov 2025 · github.com
- 18LI
2018 · languagemodels.io
- 19BS
Built a free open source agentic CLI tool for financial modeling & analysis. Hadn't played around with real equity valuation modeling for awhile and wanted to build tooling to get myself back into the game. Bull.sh lets you query & store 10-Qs, 10-K in a local vector store to chat with them, build investment thesis from scratch or build full framework models through the CLI to export into excel. It's open source, just requires your own Anthropic API key and (optionally) AlphaVantage Free API key if you want save some tokens from scraping. Feel free to play around with it. Some ideas I have…
Jan 2026 · github.com
- 20LR
I just noticed it takes literally ~5 minutes to train millions parameters on slow CPU...but before you call Yudkowsky that "it's over", an important note: the main bottleneck is the corpus size, params are just 'cleverness' but given limited info it's powerless. Anyway, here is the project: https://github.com/bggb7781-collab/lrnnsmdds/tree/main couple of notes: 1. single C file, no dependencies. Below are literally all the "dependencies", not even custom header (copy paste from the top of the single c file): #define _POSIX_C_SOURCE 200809L #include #include…
Apr 2026 · raw.githubusercontent.com
- 21TA
Nov 2025 · sequence.toys
- 22RA
Hi there, looking for feedback on my new project "Featherless.AI" The idea is to allow users to run all the models on hugging face instantly. Via the OpenAI API compatible endpoint. Why? Because its a real chore to download models and spin up GPUs, especially if you want to test multiple models. Not to mention GPUs cost multiple dollars an hour to rent. And if we want more people to use open source AI, we got to make it easier for them to try and play with all of them. So what if instead of spinning up dedicated GPUs per model (which is what every provider is doing) We can startup a LLM…
2024 · featherless.ai
- 23GR
Hi everyone, wanted to share about gline-rs, an inference engine for GLiNER models written in Rust. This family of lightweight language models proved to be efficient at zero-shot Named Entity Recognition (NER) and other tasks such as Relation Extraction, while consuming less resources than large generative models (LLMs). This implementation has been written from the ground up in Rust, and supports both span- and token-oriented variants (for inference only). The goal is to provide a production-grade and user-friendly API in a modern and safe programming language, including a clean and…
2025 · github.com
- 24IO
Hey folks, I’m the creator of WFGY — a semantic reasoning framework for LLMs. After open-sourcing it, I did a full technical and value audit — and realized this engine might be worth $8M–$17M based on AI module licensing norms. If embedded as part of a platform core, the valuation could exceed $30M. Too late to pull it back. So here it is — fully free, open-sourced under MIT. --- ### What does it solve? Current LLMs (even GPT-4+) lack *self-consistent reasoning*. They struggle with: - Fragmented logic across turns - No internal loopback or self-calibration - No modular thought units - Weak…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →