# Picolm

> SIMD/GPU pure C inference for Llama 2-family, GPT-2, Gemma-3n, and Qwen 3.x GGUF files.

- **Website:** https://github.com/whoreson/picolm
- **Pricing:** open source
- **Categories:** Developer Tools, Infrastructure
- **Tags:** developer-tools, infrastructure, design
- **Platforms:** Windows, Linux, iOS, Android
- **Last verified:** 2026-09-10
- **Canonical page:** https://linkrena.com/tools/picolm

## About

Note: MoE model GPU tensor upload is not yet supported on HIP/ROCm (CUDA works fine). MoE models on HIP fall back to CPU SSM matmul; full GPU upload path planned for next release.

MSYS2 CUDA build target: hunger-msys-direct Makefile target for MSYS2 SSH builds with nvcc+cl.exe

The original PicoLM was a clever proof-of-concept: mmap a GGUF, stream layers through 45MB of RAM, call it a day. Noble effort, but it was missing basically everything you need to actually use an LLM. So I went in and added hundreds of commits across quantization acceleration, model support, HTTP server, GPU backends, and cross-platform fixes.

Since then, progress has been steady. The main goals are (beyond satisfying curiosity on what Qwen-3.6-27B can and can't do):

First, portability. The only good software is one that runs (and is tested) on everything from the last 50 years. PicoLM runs from 32-bit MS-DOS through Raspberry Pi, MIPS/OpenWRT, AMD ROCm (MI50 tested), Metal (if someone bothers), to RTX 4090 or DGX Spark.

## Related tools

- [Supabase](https://linkrena.com/tools/supabase): Build production-grade applications with a Postgres database, Authentication, instant APIs, Realtime, Functions, Storage and Vector embeddings.
- [Hillock](https://linkrena.com/tools/hillock): Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI.
- [Shaide](https://linkrena.com/tools/shaide): Distributed, multi-model LLM inference on Kubernetes you own - axem-solutions/shaide
- [Web LLM](https://linkrena.com/tools/web-llm): High-performance In-browser LLM Inference Engine .
- [Agentic Data Kernel](https://linkrena.com/tools/agentic-data-kernel): Temporal knowledge and durable workflow infrastructure for software agents - Jason-Doyle/agentic-data-kernel
- [Pushin.eu](https://linkrena.com/tools/pushin-eu): Sovereign, GDPR-native git hosting — code, issues, and CI, all on European soil.