Answer: OpenCode automatically discovers models from Ollama, LM Studio, and vLLM at their default local addresses; you select a discovered model using the provider ID (ollama, lmstudio, or vllm) in opencode.jsonc, and for another host or port you set the OpenAI-compatible baseURL in the provider settings. Status: Overdue (check was due 2026-11-20T13:37:02Z and has not succeeded) Entry: tool/opencode/models/local-models Revision: 1 Digest: sha256:81d1525be878649f (changes whenever the content changes) Timeline: Created: 2026-11-16T13:25:38Z Last changed: 2026-11-16T13:25:38Z Last verified: 2026-11-19T13:37:02Z Next check: 2026-11-20T13:37:02Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Ollama default address | http://127.0.0.1:11434 | [1] | 2026-11-19 Ollama model example | ollama/gemma3:4b | [1] | 2026-11-19 LM Studio default address | http://127.0.0.1:1234 | [1] | 2026-11-19 LM Studio model example | lmstudio/google/gemma-4-26b-a4b | [1] | 2026-11-19 vLLM default address | http://127.0.0.1:8000 | [1] | 2026-11-19 vLLM model example | vllm/Qwen/Qwen3-Coder-30B-A3B-Instruct | [1] | 2026-11-19 Disable Ollama discovery | "plugins": ["-opencode.provider.ollama"] | [1] | 2026-11-19 Custom OpenAI-compatible package | @opencode/ai/providers/openai-compatible | [1] | 2026-11-19 Sources: [1] opencode. "Models | OpenCode". https://opencode.ai/docs/models/ Role: primary. Accessed: 2026-11-19T13:37:02Z Quote: "With Ollama listening at http://127.0.0.1:11434 , select a discovered model with the ollama provider ID" (Supports: Ollama default address) Quote: ""model" : "ollama/gemma3:4b"" (Supports: Ollama model example) Quote: "With an unauthenticated LM Studio server at http://127.0.0.1:1234 , select a discovered model with the lmstudio provider ID" (Supports: LM Studio default address) Quote: ""model" : "lmstudio/google/gemma-4-26b-a4b"" (Supports: LM Studio model example) Quote: "With vLLM listening at http://127.0.0.1:8000 , select a discovered model with the vllm provider ID" (Supports: vLLM default address) Quote: ""model" : "vllm/Qwen/Qwen3-Coder-30B-A3B-Instruct"" (Supports: vLLM model example) Quote: "Disable discovery with "plugins": ["-opencode.provider.ollama"] ." (Supports: Disable Ollama discovery) Quote: ""package" : "@opencode/ai/providers/openai-compatible"" (Supports: Custom OpenAI-compatible package) Snapshot SHA-256: 859697d5b1c7d707cd280658aaca6b793bd75b9f3111347dc1e0b865afcf857e (captured 2026-11-13T03:57:50Z) 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 2026-11-16T13:25:38Z, so the values verified then were kept. Cross-check: not-available at 2026-11-19T13:37:02Z. No independent second source is configured for this entry Last successful check: 2026-11-19T13:37:02Z Last attempt: 2026-11-19T13:37:02Z Notes and limitations: Extracted automatically from a single official source (section "Local"). Related: https://latestn.com/tool/opencode/models/model-list-endpoints-and-keys Which endpoints does opencode provide for listing models, and which require an API key? https://latestn.com/tool/opencode/models/models-available-in-codex Which models can I use with opencode Console in Codex? https://latestn.com/tool/opencode/models/raycast-go-models How do I use Go models in Raycast with OpenCode? https://latestn.com/tool/opencode/models/compaction-model Which model does opencode use for compaction and how do I change it? https://latestn.com/tool/opencode/models/console-vs-inference-model-lists What is the difference between the opencode Console model list API and the inference model list APIs? https://latestn.com/tool/opencode/models/enable-restricted-models How do I enable restricted models in OpenCode Go? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-16T13:25:38Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/opencode/models/local-models/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/opencode/models/local-models POST: https://latestn.com/dispute/tool/opencode/models/local-models with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/opencode/models/local-models?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I use local models with Ollama, LM Studio, or vLLM in opencode? Revision 1, last verified 2026-11-19T13:37:02Z. https://latestn.com/tool/opencode/models/local-models (accessed 2026-11-21T09:50:26Z). @misc{LatestN_tool_opencode_models_local_models_r1, title = {How do I use local models with Ollama, LM Studio, or vLLM in opencode?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/opencode/models/local-models}}, note = {Revision 1; digest sha256:81d1525be878649f; last verified 2026-11-19T13:37:02Z; accessed 2026-11-21T09:50:26Z} } 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/opencode/models/local-models