[PR #11090] New Memory Management #13437

Closed
opened 2026-04-13 00:27:18 -05:00 by GiteaMirror · 0 comments
Owner

Original Pull Request: https://github.com/ollama/ollama/pull/11090

State: closed
Merged: Yes


This changes the memory allocation strategy from upfront estimation to tracking actual allocations done by the engine and reacting to that. The goal is avoid issues caused by both under-estimation (crashing) and over-estimation (low performance due to under-utilized GPUs).

It is currently opt-in and can be enabled for models running on the Ollama engine by setting OLLAMA_NEW_ESTIMATES=1. Behavior in other cases is unchanged and will continue to use the existing estimates.

**Original Pull Request:** https://github.com/ollama/ollama/pull/11090 **State:** closed **Merged:** Yes --- This changes the memory allocation strategy from upfront estimation to tracking actual allocations done by the engine and reacting to that. The goal is avoid issues caused by both under-estimation (crashing) and over-estimation (low performance due to under-utilized GPUs). It is currently opt-in and can be enabled for models running on the Ollama engine by setting OLLAMA_NEW_ESTIMATES=1. Behavior in other cases is unchanged and will continue to use the existing estimates.
GiteaMirror added the pull-request label 2026-04-13 00:27:18 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#13437