PureBee/purebee
A GPU defined in software. Runs Llama 3.2 1B at 3.6 tok/sec. Zero dependencies.
PureBee allows developers to run large language models like Llama 3.2 1B on any device using only a CPU, without needing a dedicated graphics card or complex drivers. It takes a language model as input and produces text responses, making advanced AI inference accessible on standard computing environments. This tool is for developers building applications where they need to integrate AI capabilities into environments lacking specialized GPU hardware.
Use this if you are a developer who needs to embed AI inference capabilities directly into applications running on standard CPUs, without reliance on GPU hardware or specific graphics drivers.
Not ideal if you already have access to powerful GPUs and are seeking the absolute fastest inference speeds, as PureBee prioritizes accessibility over raw computational power.
Stars
22
Forks
7
Language
JavaScript
License
—
Category
Last pushed
Feb 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/PureBee/purebee"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
alibaba/MNN
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering...
xorbitsai/inference
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source,...
tensorzero/tensorzero
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM...