Is Ollama v0.40.8 safe to update?

Probably yes. Bug fixes and minor features only, per the release notes. No breaking changes mentioned.

What users are reporting

5 public report(s) mention this version, none clearly describing breakage. Most-discussed: “Error: 500 Internal Server Error with new model Flint”. Sources: GitHub · checked 2026-10-22

• Error: 500 Internal Server Error with new model Flint (GitHub, closed)
• [Vulkan][AMD RADV] ~30× generation slowdown after first request with prompt cache enabled — Ollama 0.40.8 (GitHub)
• Pending eviction (OLLAMA_MAX_LOADED_MODELS=1) is cancelled when a request for the resident model carries keep_alive; waiting request stalls (GitHub)
• Calls to a function that isn't in the request's tools are dropped silently (empty response, eval_count > 0) (GitHub)
• Flint: integer tool-call arguments in history are re-emitted as float strings (30000 -> "30000.0") (GitHub)

Reports are from public issue trackers and forums. Their count isn't a failure rate, and an empty list doesn't prove an update is safe.

⚠️ What breaks

Nothing in the release notes suggests breaking changes. This looks like a bug-fix or minor release. The usual precautions (backup, read notes) still apply.

Read the full official release notes →

✅ What to do first

1. Read the official release notes (linked in “What breaks”).
2. Back up config and data (snapshot the VM/volume if you can).
3. Note the version you are on now, so you can roll back.
4. Update, then check logs and core functions before walking away.

↩️ How to roll back to v0.40.7

Docker: snapshot/back up the data volumes first, then if needed change the tag back, e.g. image: ollama/ollama:v0.40.7, and run docker compose up -d. Tag format varies by image (some drop the “v”), so check the registry’s tag list.