docker / docker/model-runner

Gemma 4 on llama: Reasoning budget 0 does not work

Open
#1,039 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Go
Stars
651
Forks
155
PR merge metrics
No merged PRs in 30d

Description

models:
  llm:
    model: ai/gemma4:e2b
    runtime_flags:
      - "--reasoning-budget"
      - "0"

When using this configuration on MacOS, the model outputs its reasoning inside the answers's content ie: "The user wants ...."

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the Docker Model Runner configuration on macOS with ai/gemma4:e2b and reasoning-budget set to 0. Trace how the runtime flag is handled and verify that reasoning is excluded from the answer content when the setting is applied.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker
Domain
ai
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.