The Ollama game logo

Ollama

PatchBot will keep your Discord channel up-to-date on all the latest Ollama patch notes.

Servers
109
Gamers
52,242

Latest Updates

v0.17.1

What's Changed
* models: add nemotron architecture support by @jmorganca in [#14356](https://github.com/ollama/ollama/pull/14356) * Avoid Excessive MLX Memory Usage by @jessegross in [#14341](https://github.com/ollama/ollama/pull/14341) * ui: use capability-based detection for web search by @hoyyeva in [#14336](https://github.com/ollama/ollama/pull/14336) * mlxrunner: Fix duplicate log prefixes and reduce log noise by @jessegross in [#14379](https://github.com/ollama/ollama/pull/14379) ...

v0.17.1

What's Changed
* models: add nemotron architecture support by @jmorganca in [#14356](https://github.com/ollama/ollama/pull/14356) * Avoid Excessive MLX Memory Usage by @jessegross in [#14341](https://github.com/ollama/ollama/pull/14341) * ui: use capability-based detection for web search by @hoyyeva in [#14336](https://github.com/ollama/ollama/pull/14336) * mlxrunner: Fix duplicate log prefixes and reduce log noise by @jessegross in [#14379](https://github.com/ollama/ollama/pull/14379) ...

v0.17.1

What's Changed
* models: add nemotron architecture support by @jmorganca in [#14356](https://github.com/ollama/ollama/pull/14356) * Avoid Excessive MLX Memory Usage by @jessegross in [#14341](https://github.com/ollama/ollama/pull/14341) * ui: use capability-based detection for web search by @hoyyeva in [#14336](https://github.com/ollama/ollama/pull/14336) * mlxrunner: Fix duplicate log prefixes and reduce log noise by @jessegross in [#14379](https://github.com/ollama/ollama/pull/14379) ...

v0.17.1

What's Changed
* models: add nemotron architecture support by @jmorganca in [#14356](https://github.com/ollama/ollama/pull/14356) * Avoid Excessive MLX Memory Usage by @jessegross in [#14341](https://github.com/ollama/ollama/pull/14341) * ui: use capability-based detection for web search by @hoyyeva in [#14336](https://github.com/ollama/ollama/pull/14336) * mlxrunner: Fix duplicate log prefixes and reduce log noise by @jessegross in [#14379](https://github.com/ollama/ollama/pull/14379) ...

v0.17.0

What's Changed
* Improved tokenizer performance * Ollama's macOS and Windows apps will now default to a context length based on available VRAM
New Contributors
* @natl-set made their first contribution in [#14322](https://github.com/ollama/ollama/pull/14322)

v0.17.0

What's Changed
* mlx: try loading library via rpath before searching directories by @natl-set in [#14322](https://github.com/ollama/ollama/pull/14322) * consolidate the tokenizer by @pdevine in [#14327](https://github.com/ollama/ollama/pull/14327) * app: expose server's default context length to UI by @jmorganca in [#14037](https://github.com/ollama/ollama/pull/14037) * cmd: openclaw onboarding by @ParthSareen in [#14344](https://github.com/ollama/ollama/pull/14344)
New Contributors
...