{"schemaVersion":1,"id":"lm-studio-local","revision":"2026-09-15.1","name":"LM Studio (local runtime)","monogram":"LM","category":"Packaged runtime","openness":"Not established","license":"Proprietary app terms; bundled engines and model weights have separate licenses","color":"#d394e7","summary":"Desktop runtime management and local serving through llama.cpp or MLX engines.","website":"https://lmstudio.ai","repository":"","environment":"Local LM Studio app and server; pin the separately installed llama.cpp or MLX engine. Excludes remote hosts, Bionic workflows and external tools.","contributor":"Testedknowhow model runtime research","affiliation":"Commissioned by a Nimbalyst maintainer. Documentation synthesis; no independent review or product execution.","contentLicense":"Unlicensed prototype; redistribution decision pending","reviewStatus":"unreviewed","lastChecked":"2026-09-15","expiresAt":"2026-10-15","applicability":{"versions":["Living documentation accessed 2026-09-15; app and installed engine versions are not pinned."],"environment":"Local LM Studio app and server; pin the separately installed llama.cpp or MLX engine. Excludes remote hosts, Bionic workflows and external tools.","excludes":["Runtime verification and performance rankings","Model weights license or quality evaluation","Cloud inference, remote hosts and external tools","Unlisted model architectures, builds and hardware"]},"claims":[{"id":"lm-studio-local-rt-local","capability":"rt-local","statement":"Local chat and server operation can work offline.","method":"documented","outcome":"claimed","scope":"Download models and runtimes first; discovery, downloads and app updates need connectivity.","evidenceIds":["lm-studio-local-offline"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-apple-silicon","capability":"rt-apple-silicon","statement":"Supports Apple Silicon Macs and the MLX engine.","method":"documented","outcome":"claimed","scope":"Check the documented macOS and hardware requirements; Intel Mac support is not implied.","evidenceIds":["lm-studio-local-app"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-gguf","capability":"rt-gguf","statement":"Runs supported GGUF models with its llama.cpp engine.","method":"documented","outcome":"claimed","scope":"Engine version is independently managed; supported model architectures only.","evidenceIds":["lm-studio-local-app"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-mlx","capability":"rt-mlx","statement":"Runs supported MLX models on Apple Silicon.","method":"documented","outcome":"claimed","scope":"MLX engine only; does not imply GGUF and MLX artifacts are interchangeable.","evidenceIds":["lm-studio-local-app"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-http","capability":"rt-http","statement":"Provides a local inference server.","method":"documented","outcome":"claimed","scope":"Local inference with preloaded models; remote tools are excluded.","evidenceIds":["lm-studio-local-offline"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-openai","capability":"rt-openai","statement":"Exposes an OpenAI-style chat-completions endpoint.","method":"documented","outcome":"claimed","scope":"Documented request fields only; no complete OpenAI API parity claim.","evidenceIds":["lm-studio-local-chat"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-streaming","capability":"rt-streaming","statement":"Supports streaming in the chat-completions API.","method":"documented","outcome":"claimed","scope":"stream request parameter; compatible local model and engine.","evidenceIds":["lm-studio-local-chat"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-structured","capability":"rt-structured","statement":"Accepts JSON schema constraints for generation.","method":"documented","outcome":"claimed","scope":"GGUF uses llama.cpp grammars and MLX uses Outlines; reliability varies by model.","evidenceIds":["lm-studio-local-structured"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-speculative","capability":"rt-speculative","statement":"Provides draft-model speculative decoding.","method":"documented","outcome":"claimed","scope":"Main and draft vocabularies must match; added resource use may slow generation.","evidenceIds":["lm-studio-local-speculative"],"contradictions":[],"support":"yes"},{"id":"lm-studio-local-rt-concurrent","capability":"rt-concurrent","statement":"Documents parallel requests for the llama.cpp engine; MLX support is listed as forthcoming.","method":"documented","outcome":"claimed","scope":"Partial across the target engines: llama.cpp continuous batching only at capture date; configure Max Concurrent Predictions.","evidenceIds":["lm-studio-local-concurrent"],"contradictions":[],"support":"partial"}],"evidence":[{"id":"lm-studio-local-app","url":"https://lmstudio.ai/docs/app","title":"LM Studio app documentation","locator":"Run llama.cpp (GGUF) or MLX models; runtime management; local serving","capturedAt":"2026-09-15","kind":"vendor-documentation","revision":null,"redistribution":"Link and original paraphrase only; upstream rights retained."},{"id":"lm-studio-local-offline","url":"https://lmstudio.ai/docs/app/offline","title":"LM Studio offline operation","locator":"Local chat and server; operations requiring connectivity","capturedAt":"2026-09-15","kind":"vendor-documentation","revision":null,"redistribution":"Link and original paraphrase only; upstream rights retained."},{"id":"lm-studio-local-hardware","url":"https://lmstudio.ai/docs/app/system-requirements","title":"LM Studio system requirements","locator":"Apple Silicon and macOS requirements","capturedAt":"2026-09-15","kind":"vendor-documentation","revision":null,"redistribution":"Link and original paraphrase only; upstream rights retained."},{"id":"lm-studio-local-concurrent","url":"https://lmstudio.ai/docs/app/advanced/parallel-requests","title":"LM Studio parallel requests","locator":"Max Concurrent Predictions; engine support","capturedAt":"2026-09-15","kind":"vendor-documentation","revision":null,"redistribution":"Link and original paraphrase only; upstream rights retained."},{"id":"lm-studio-local-structured","url":"https://lmstudio.ai/docs/developer/openai-compat/structured-output","title":"LM Studio structured output","locator":"JSON schema response_format; llama.cpp grammars; MLX Outlines; model limitations","capturedAt":"2026-09-15","kind":"vendor-documentation","revision":null,"redistribution":"Link and original paraphrase only; upstream rights retained."},{"id":"lm-studio-local-chat","url":"https://lmstudio.ai/docs/developer/openai-compat/chat-completions","title":"LM Studio chat-completions endpoint","locator":"POST /v1/chat/completions; stream parameter","capturedAt":"2026-09-15","kind":"vendor-documentation","revision":null,"redistribution":"Link and original paraphrase only; upstream rights retained."},{"id":"lm-studio-local-speculative","url":"https://lmstudio.ai/docs/app/advanced/speculative-decoding","title":"LM Studio speculative decoding","locator":"Draft model selection; vocabulary compatibility; resource tradeoffs","capturedAt":"2026-09-15","kind":"vendor-documentation","revision":null,"redistribution":"Link and original paraphrase only; upstream rights retained."},{"id":"lm-studio-local-terms","url":"https://lmstudio.ai/app-terms","title":"LM Studio app terms","locator":"Version August 23, 2026; License Grant; Restrictions On Use","capturedAt":"2026-09-15","kind":"vendor-documentation","revision":"2026-08-23","redistribution":"Link and original paraphrase only; upstream rights retained."}],"gaps":["Which pinned model, quantization, context length and runtime versions fit the selected Mac?","What are measured latency, throughput, peak memory and swap under one and four concurrent requests?","The schema has no proprietary source-access value: Not established does not override the explicitly recorded proprietary app terms."],"invalidationTriggers":["Runtime, bundled engine, backend, model format or license changes.","Documentation changes affecting the cited configuration."],"verificationPlan":["Choose hardware and obtain explicit approval for installations, downloads and execution resources.","Pin runtime and engine versions, model artifact hashes, tokenizer, template, quantization and inference settings.","Run the local-model-mac investigation with synthetic prompts and capture raw measurements; do not record documentation as execution."],"attestations":[],"space":"model-runtimes"}