ggml llama.cpp releases

new version

ggml llama.cpp is tracked under self-hosted apps & servers. Its latest version, 0.4.1, shipped on Sep 14, 2026.

Latest version
0.4.1
Released
Category
Self-hosted apps & servers
Last checked

How to update ggml llama.cpp

Open update page ↗
  1. Read the release notes first — self-hosted projects break config and schemas between versions more often than appliances do.
  2. Docker: pull the new image tag and recreate the container (`docker compose pull && docker compose up -d`).
  3. Package or bare metal: update through your distribution's package manager, or replace the binary from the releases page.
  4. Back up the config and database directory first. For most projects a downgrade is not supported once the schema has migrated.

Always download firmware from the manufacturer or project itself. Firmwarely links out; it never hosts firmware.

What changed

Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0. API changes Changed llama_sampler_chain_n() to return int32_t instead of int (#​28631). Added serv…

Manufacturer release notes ↗

Version history

0.4.1

FAQ

What is the latest version of ggml llama.cpp?

Version 0.4.1, released Sep 14, 2026. This page is refreshed every 30 minutes from the manufacturer's release page.

How do I update ggml llama.cpp?

See the step-by-step above. Pull the new image or package and restart the service. Read the release notes and back up the data directory first; most projects can't downgrade once the database has migrated.

How does Firmwarely know when there's a new version?

Every 30 minutes we read the manufacturer's official release page for the ggml llama.cpp and record the version, date and changelog. Subscribers watching this device get one email a day when it changed.

Is this an official ggml page?

No. Firmwarely is independent. Project and product names belong to their owners; always install releases from the project's own source.

Get alerts for ggml llama.cpp

One email when a new or critical firmware ships. Free for up to 3 devices.