# Ollama runner no-mmap default on Metal and use_mmap option > 2024-06: maintainer advised {"options": {"use_mmap": false}} to cure thrashing (issue 3940). Parent: [Mac local LLMs: Ollama internals](https://llms-explorer.com/tree/mac-local-llms-ollama-internals/) · 1 facets · 22 facts · page: https://llms-explorer.com/tree/ollama-runner-no-mmap-default-on-metal-and-use-m/ ## Facts - 2024-06: maintainer advised {"options": {"use_mmap": false}} to cure thrashing (issue 3940). — source: `asserted` - 2024-09: PR 6854 proposed OLLAMA_NO_MMAP to force --no-mmap globally; no maintainer merge is visible on the page. — source: `asserted` - 2025-01 and 2025-04 logs show --no-mmap on Metal and Linux partial offload (issues 8571, 10104, 7081). — source: `asserted` - By v0.12.0 the loader is split into an Ollama engine (no mmap) and a llama engine (mmap rules above). — source: `asserted` - Layer count: the Metal rule triggers on NumGPU between 1 and block_count, so a model Ollama decides to split (for example 9 of 62 layers) always loads with no mmap, which cannot load a model larger than RAM. — source: `asserted` - Forcing mmap on is only possible per request or Modelfile (use_mmap true), not with an environment variable. — source: `asserted` - Disabling mmap crashed some models in a 2024 report even with fewer layers (issue 3940). — source: `asserted` - Reporters in issue 4895 say --no-mmap is slightly faster and avoids RAM spikes on 8 GB machines; the Ollama staff reply in PR 6854 asks whether mmap should instead be disabled by default. Not resolved on the page. — source: `asserted` - Whether PR 6854 was merged (page shows no merged marker; "Closed" appears twice, which I read as closed unmerged but did not verify). — source: `asserted` - Behavior in releases after v0.12.0; the main-branch llm/server.go fetched here is a 289-line stub with no mmap logic. — source: `asserted` - Ollama's code comment reads "mmap has issues with partial offloading on metal" and sets UseMMap to false when a metal GPU has 0 < NumGPU < BlockCount + 1. — [source](https://raw.githubusercontent.com/ollama/ollama/v0.6.2/llm/server.go) - In v0.6.2, --no-mmap is appended when (Windows, CUDA, UseMMap nil) or (Linux, free memory < estimated total, UseMMap nil) or (CPU library, UseMMap nil) or UseMMap explicitly false. — [source](https://raw.githubusercontent.com/ollama/ollama/v0.6.2/llm/server.go) - The same rules appear in v0.12.0 as loadRequest.UseMmap = false, and v0.12.0 notes "Mmap is only supported on the llama engine"; the Ollama engine path leaves the legacy UseMmap field unused. — [source](https://raw.githubusercontent.com/ollama/ollama/v0.12.0/llm/server.go) - Ollama's Options struct has UseMMap *bool with JSON name use_mmap, and the default options set UseMMap to nil. — [source](https://raw.githubusercontent.com/ollama/ollama/main/api/types.go) - A Metal log (Ollama.app, 2025-01-24) offloading 9 of 62 layers of a 413.6 GiB model on a 48 GiB machine shows --n-gpu-layers 9 --no-mmap. — [source](https://github.com/ollama/ollama/issues/8571) - A Linux log (Ollama 0.6.2, 2025-04-03) shows --n-gpu-layers 21 --no-mmap and "load_tensors ... (mmap = false)" for a 250 GB model. — [source](https://github.com/ollama/ollama/issues/10104) - A maintainer's workaround for forcing mmap is the client option {"use_mmap": true}; ollama serve --help and ollama run --help expose no mmap flag. — [source](https://github.com/ollama/ollama/issues/10104) - A 2024-06 maintainer reply tells a user whose model thrashed to send options {"use_mmap": false}, and the user reported it "works nicely"; a second user saw crashes with mmap disabled unless num_gpu was also reduced. — [source](https://github.com/ollama/ollama/issues/3940) - PR 6854 proposed OLLAMA_NO_MMAP=1 to always add --no-mmap to the llama runner; a reviewer asked what problem mmap caused and whether it should be off by default, and commenters later asked for updates and for a way to force mmap on. — [source](https://github.com/ollama/ollama/pull/6854) - Issue 4895 requested a global use_mmap environment variable because many front ends cannot set it; the reporter claims --no-mmap costs 5-10 s more load time on an 8 GB RAM, 6 GB VRAM PC but avoids RAM at 99 percent. — [source](https://github.com/ollama/ollama/issues/4895) - Issue 10539 (2025-05-02, Ollama 0.6.7, closed) asked for a global use_mmap variable after reporting that with use_mmap true, model RAM was not fully released after unload and load times were worse. — [source](https://github.com/ollama/ollama/issues/10539) - On a Mac, a model that fits fully on the GPU loads with mmap by default under the llama engine, so its weights are reclaimable file cache until Metal touches them; a split model loads into anonymous memory. — source: `asserted`