small-models

Bonsai Demo

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

Generate images locally

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

OpenSSA: Small Specialist Agents based on Domain-Aware Neurosymbolic Agent (DANA) architecture for industrial problem-solving

🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.

Coding agent built around small (<10B) models for local development with a Rust (Actix Web, Diesel)/Typescript (Solid, Tailwind) opinionated stack. No coding knowledge needed. Multiple agents and roles - Product Owner, PM, Engineering Manager, Rust Engineer, SolidJS Engineer, etc. work together to build full-stack apps.

Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models

[CVPR 2024] Asymmetric Masked Distillation for Pre-Training Small Foundation Models

This repository features a custom-built decoder-only language model (LLM) with a total of 37 million parameters 🔥. I train the model to be able to ask question from a given context

BobVLM – A 1.5B multimodal model built from scratch and pre-trained on a single P100 GPU capable of image descriptions and moderate question answering. 🤗🎉

Overview of self-supervised learning of tiny models, including distillation-based methods (aks. self-supervised distillation) and non-distillation methods.

A lightweight Ollama desktop client optimized for low-end PCs, integrated graphics, and small local models.

Code for "On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small Models"

🪴🪨

Compact coding-discipline skill for AI agents on small/local models — Karpathy guidelines × Superpowers loop in <500 words

quickthink is a local-first CLI and Python library that wraps Ollama-backed LLM calls with a compressed plan-then-answer scaffold and latency-aware routing. It adds a short validated planning step for multi-step prompts and routes simple ones straight through. Local inference control for small models.

If OpenAI builds engines, VOID builds the chassis.

MoroAI is a local-first model adaptation foundry for building, evaluating, and deploying private small language models from your own data.

Help us define the Pareto front of small models for MNIST classification. Frugal AI.