Welcome to Pump.fun!
Pump lets anyone create coins, giving everyone equal access to buy and sell from the start. Prices can move quickly, so trade carefully.
By clicking this button, you agree to the Terms and Conditions, Privacy Policy, and certify that you are over 18 years old.
$AIRLLM
With over 24k GitHub stars and 2.7k forks, AirLLM is redefining how far a single consumer GPU can stretch. AirLLM lets you run massive LLMs on tiny consumer GPUs without quantization, distillation, or pruning. It works out of the box with almost every popular open model family, Llama, Qwen, DeepSeek, Mistral, Mixtral, Phi, Gemma, ChatGLM, Baichuan, InternLM, all through one AutoModel line. It recently became one of the most recognized low resource inference projects in the open source LLM ecosystem. Dev is onboarded and will claim 100%