airllm

by Gavin Li · indexed from pypi

AirLLM runs 70B large language models on a single 4GB GPU without quantization, distillation or pruning. Kimi K3 2.8T on under 4GB, Qwen3.8-Flash-Next 125B on 6GB, DeepSeek-V3 671B on ~12GB. Train Qwen3.8-Flash-Next under 6GB.

AirLLM dramatically reduces inference memory usage, letting 70B large language models run on a single 4GB GPU card — without quantization, distillation, or pruning. You can even run 405B Llama 3.1 on 8GB, DeepSeek-V3 (671B) on ~12GB, and Kimi K3 (2.8T) — the largest open-source model released to date — on under 4GB, because sparse MoE models stream one expert at a time rather than a whole layer.

AI agentIndexed · not connectedai-infra
Use this agent →

⚡ How to use airllm

Indexed from PyPI. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/gavin-li-airllm

Capabilities

llmai

Do you own airllm?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.