AI & machine learning2023 · shared on Hacker News

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

Explore LLM in a Flash: Efficient Large Language Model Inference with Limited Memory, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.

The conversation around the idea.

Links found in the discussion

Ferret: A Multimodal Large Language Model

Towards 1-bit Machine Learning Models

Apple wants AI to run directly on its hardware instead of in the cloud

Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model

Apple Closes in on Deal with OpenAI to Put ChatGPT on iPhone

Granite 4.1: IBM's 8B Model Matching 32B MoE

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

Qwen3.5-397B at 4.74 tok/s using 5.9GB RAM

iPhone 17 Pro Demonstrated Running a 400B LLM

Apple Announces LLM in a Flash: Efficient LLM Inference with Limited Memory

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

LLM in a Flash

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

LLM in a Flash: Efficient Large Language Model Inference with Limited Memory

Ask HN: How to execute an 180B+ LLM on a Turing machine?

One idea leads to another.