Shimmy v2.0
The first pure-Rust GGUF inference engine. No C. No Python.
What it does
Two 5,200-token runs. Same model. SHA-identical byte output. That's a proof, not a benchmark. Shimmy v2.0 ships Airframe: pure-Rust GPU inference with hand-written WGSL compute shaders. No llama.cpp. No C. No Python. No CUDA. First production GGUF engine Rust all the way down — including the GPU shaders. Run TinyLlama, Llama 3.2, Phi, DeepSeek from GGUF. Drop-in for AnythingLLM, Open WebUI, Cursor, Zed via OpenAI or Ollama API. Windows, macOS, Linux. cargo install shimmy
Does the same job
all alternatives →- WMWe made our own inference engine for Apple Silicon2025 · github.com · ▲186
We wrote our inference engine on Rust, it is faster than llama cpp in all of the use cases. Your feedback is very welcomed. Written from scratch with idea that you can add support of any kernel and platform.
- OSOpen-source engine running Gemma 4 26B in 2 GB RAM on any M-series MacJul 2026 · github.com · ▲919
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…
- FLFinetune LLaMA-7B on commodity GPUs using your own text2023 · github.com · ▲449
I've been playing around with https://github.com/zphang/minimal-llama/ and https://github.com/tloen/alpaca-lora/blob/main/finetune.py, and wanted to create a simple UI where you can just paste text, tweak the parameters, and finetune the model quickly using a modern GPU. To prepare the data, simply separate your text with two blank lines. There's an inference tab, so you can test how the tuned model behaves. This is my first foray into the world of LLM finetuning, Python, Torch, Transformers, LoRA, PEFT, and Gradio. Enjoy!
- RRRunNburn – Run a 295B Moe from a 98GB GGUF on a 64GB RAM DesktopJul 2026 · github.com · ▲11
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…
- CRcuTile Rust: Safe, data-race-free GPU kernels in RustJun 2026 · github.com · ▲106
- CFCuq – Formal Verification of Rust GPU KernelsOct 2025 · github.com · ▲94
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com