Alternatives
Products that do what Run Full Kimi K3 with 29 GB of RAM does
Run the full 2.78-trillion-parameter Kimi K3 model or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine. - sqliteai/warp
- 1
- 2AN
Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights. It clearly does not fit in the memory of a laptop. But K3 is a Mixture-of-Experts model. For each token, only a small fraction of its 896 experts per layer is activated. That changes the problem: the entire model does not need to be resident in RAM, as long as the weights required by each token can be reached quickly enough. We built WASTE — the Weight-Aware Streaming Tensor Engine — to explore that idea. WASTE keeps the dense, repeatedly used part of the model resident in memory, stores the routed experts in an…
Jul 2026
- 3
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
- 4
- 5
- 6ZΜ
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64KB RAM. The entire thing: inference, weights, chat UI, it all fits in a 40KB .COM file that you can run in a CP/M emulator and hopefully even real hardware! It won't write your emails, but it can be trained to play a stripped down version of 20 Questions, and is sometimes able to maintain the illusion of having simple but terse conversations…
Dec 2025 · github.com
- 7
General Compute▲315AI models that run on an inference cloud optimized for speed
May 2026 · generalcompute.com
- 8EL
2023 · github.com
- 9GG
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
- 10
- 11
I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next Local models really are the future of computing!
5d ago · github.com
- 12SF
Hey folks! We're Alex and Evan, and we're working on putting together a 512 H100 compute cluster for startups and researchers to train large generative models on. - it runs at the lowest possible margins (<$2.00/hr per H100) - designed for bursty training runs, so you can take say 128 H100s for a week - you don’t need to commit to multiple years of compute or pay for a year upfront Big labs like OpenAI and Deepmind have big clusters that support this kind of bursty allocation for their researchers, but startups so far have had to get very small clusters on very long term contracts, wait…
2023 · sfcompute.org
- 13
- 148F
Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
2023 · github.com
- 15
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. - MakazhanAlpamys/Soup
Aug 2026 · github.com
- 16SU
Here's a project I've been working on for the last few months. It's a new (I think) algorithm, that allows to adjust smoothly - and in real time - how many calculations you'd like to do during inference of an LLM model. It seems that it's possible to do just 20-25% of weight multiplications instead of all of them, and still get good inference results. I implemented it to run on M1/M2/M3 GPU. The mmul approximation itself can be pushed to run 2x fast before the quality of output collapses. The inference speed is just a bit faster than Llama.cpp's, because the rest of implementation…
2024 · asciinema.org
- 17AT
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
- 18
- 19RQ
Sep 2025 · github.com
- 20
- 21
- 22
- 23OP
Open Prompts is the dataset used to build krea.ai. The data comes from the Stability AI Discord and includes around 10M images from 2M prompts. You can use it for creating semantic search engines of prompts, training LLMs, fine-tuning image-to-text models like BLIP, or extracting insights from the data—like the most common combinations of modifiers.
2022 · github.com
- 24KR
I discovered that in LLM inference, keys and values in the KV cache have very different quantization sensitivities. Keys need higher precision than values to maintain quality. I patched llama.cpp to enable different bit-widths for keys vs. values on Apple Silicon. The results are surprising: - K8V4 (8-bit keys, 4-bit values): 59% memory reduction with only 0.86% perplexity loss - K4V8 (4-bit keys, 8-bit values): 59% memory reduction but 6.06% perplexity loss - The configurations use the same number of bits, but K8V4 is 7× better for quality This means you can run LLMs with 2-3× longer…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →