[GH-ISSUE #584] Add support for OpenAI's gpt-oss open weight models #93

New issue

Open

opened 2026-03-03 13:52:54 +03:00 by kerem · 0 comments

kerem commented

2026-03-03 13:52:54 +03:00

Owner

Originally created by @0xdevalias on GitHub (Aug 28, 2025).
Original GitHub issue: https://github.com/jehna/humanify/issues/584

https://openai.com/open-models/
- Open models by OpenAI
- gpt-oss-120b
  A large open model designed to run in data centers and on high-end desktops and laptops.
- gpt-oss-20b
  A medium-sized open model that can run on most desktops and laptops.
https://node-llama-cpp.withcat.ai/blog/v3.12-gpt-oss
- gpt-oss is here!
- August 10, 2025
- node-llama-cpp v3.12 is here, with full support for gpt-oss models!
- gpt-oss
  
  gpt-oss comes in two flavors:
  - gpt-oss-20b - 21B parameters with 3.6B active parameters
  - gpt-oss-120b - 117B parameters with 5.1B active parameters
  Here are a few highlights of these models:
  - Due to the low number of active parameters, these models are very fast
  - These are reasoning models, and you can adjust their reasoning effort
  - They are very good at function calling, and are built with agentic capabilities in mind
  - These models were trained with native MXFP4 precision, so no need to quantize them further. They're small compared to their capabilities already
  - They are provided with an Apache 2.0 license, so you can use them in your commercial applications

https://github.com/jehna/humanify/pull/582
https://github.com/jehna/humanify/pull/568
https://github.com/jehna/humanify/pull/565
https://github.com/jehna/humanify/issues/400
https://github.com/jehna/humanify/pull/646
- This adds the ollama command that can be used and uses the default model gpt-oss:20b
https://github.com/jehna/humanify/pull/647

Originally created by @0xdevalias on GitHub (Aug 28, 2025). Original GitHub issue: https://github.com/jehna/humanify/issues/584 - https://openai.com/open-models/ - > Open models by OpenAI - > `gpt-oss-120b` > A large open model designed to run in data centers and on high-end desktops and laptops. - > `gpt-oss-20b` > A medium-sized open model that can run on most desktops and laptops. - https://node-llama-cpp.withcat.ai/blog/v3.12-gpt-oss - > gpt-oss is here! - > August 10, 2025 - > [`node-llama-cpp`](https://node-llama-cpp.withcat.ai/) v3.12 is here, with full support for [`gpt-oss`](https://huggingface.co/openai/gpt-oss-20b) models! - > ## gpt-oss > > [`gpt-oss`](https://huggingface.co/openai/gpt-oss-20b) comes in two flavors: > > - [`gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) - 21B parameters with 3.6B active parameters > - [`gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) - 117B parameters with 5.1B active parameters > > Here are a few highlights of these models: > > - Due to the low number of active parameters, these models are very fast > - These are reasoning models, and you can adjust their reasoning effort > - They are very good at function calling, and are built with agentic capabilities in mind > - These models were trained with native MXFP4 precision, so no need to quantize them further. They're small compared to their capabilities already > - They are provided with an Apache 2.0 license, so you can use them in your commercial applications ## See Also - https://github.com/jehna/humanify/pull/582 - https://github.com/jehna/humanify/pull/568 - https://github.com/jehna/humanify/pull/565 - https://github.com/jehna/humanify/issues/400 - https://github.com/jehna/humanify/pull/646 - > This adds the `ollama` command that can be used and uses the default model `gpt-oss:20b` - https://github.com/jehna/humanify/pull/647