Answer: To set up local model routing with a Gemma model, download the LiteRT-LM runtime for your system, download the Gemma model (e.g., gemma3-1b-gpu-custom) via the runtime, then start the runtime on a chosen port such as 9379. The Gemma model must be running locally, served behind an HTTP endpoint and accessed via the Gemini API. Status: Confirmed Entry: tool/gemini-cli/models/manual-local-model-routing-setup Revision: 1 Digest: sha256:ba33f7f8407db3be (changes whenever the content changes) Timeline: Created: 2026-11-13T03:18:14Z Last changed: 2026-11-13T03:18:14Z Last verified: 2026-11-20T12:52:25Z Next check: 2026-11-21T12:52:25Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Unit | Source | As of model | gemma3-1b-gpu-custom | | [1] | 2026-11-20 example port | 9379 | | [1] | 2026-11-20 example serve command | ./lit.macos_arm64 serve --port=9379 --verbose | | [1] | 2026-11-20 runtime | LiteRT-LM | | [1] | 2026-11-20 model download size | 968.6 MB | MB | [1] | 2026-11-20 Sources: [1] Google. "Manual Local Model Routing Setup (experimental)". https://geminicli.com/docs/core/local-model-routing.md Role: primary. Accessed: 2026-11-20T12:52:25Z Quote: "pull gemma3-1b-gpu-custom" (Supports: model) Quote: "we will use port `9379`" (Supports: example port) Quote: "Example command for MacOS: `./lit.macos_arm64 serve --port=9379 --verbose`" (Supports: example serve command) Quote: "The [LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM) runtime offers" (Supports: runtime) Quote: "Downloading... 968.6 MB" (Supports: model download size) Published: 2026-10-16T02:36:07Z Snapshot SHA-256: 29112d988b3dd4a7f3629d29600541554d066acfe2537b372f4a0b1cb6fc3f47 (captured 2026-11-13T03:18:14Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T03:18:14Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:52:25Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:52:25Z Last attempt: 2026-11-20T12:52:25Z Notes and limitations: Extracted automatically from a single official source (section "Manual Setup"). Related: https://latestn.com/tool/gemini-cli/models/model-config-resolution-order How does Gemini CLI resolve which model configuration to use when both aliases and overrides are set? https://latestn.com/tool/gemini-cli/models/model-fallback How does model fallback work in Gemini CLI? https://latestn.com/tool/gemini-cli/models/model-options What model options are available in Gemini CLI's /model command? https://latestn.com/tool/gemini-cli/models/generation-parameters-reference Which generation parameters like temperature and topP can I configure in Gemini CLI? https://latestn.com/tool/gemini-cli/models/launch-specific-gemini-3-model How do I launch a specific Gemini 3 model directly in Gemini CLI? https://latestn.com/tool/gemini-cli/models/local-model-routing How do I enable or configure local model routing with Gemma in Gemini CLI? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:18:14Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/gemini-cli/models/manual-local-model-routing-setup/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/gemini-cli/models/manual-local-model-routing-setup POST: https://latestn.com/dispute/tool/gemini-cli/models/manual-local-model-routing-setup with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/gemini-cli/models/manual-local-model-routing-setup?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I set up local model routing with a Gemma model in Gemini CLI? Revision 1, last verified 2026-11-20T12:52:25Z. https://latestn.com/tool/gemini-cli/models/manual-local-model-routing-setup (accessed 2026-11-21T09:56:38Z). @misc{LatestN_tool_gemini_cli_models_manual_local_model_routing_setup_r1, title = {How do I set up local model routing with a Gemma model in Gemini CLI?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/gemini-cli/models/manual-local-model-routing-setup}}, note = {Revision 1; digest sha256:ba33f7f8407db3be; last verified 2026-11-20T12:52:25Z; accessed 2026-11-21T09:56:38Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/gemini-cli/models/manual-local-model-routing-setup