Packaged runtime / PRODUCT DOSSIER

LM Studio (local runtime)

Desktop runtime management and local serving through llama.cpp or MLX engines.

Investigation: Which local model runtime fits a 32GB or 64GB Mac? →

Official website ↗Explore in graph →10 cited claims ↓

Local LM Studio app and server; pin the separately installed llama.cpp or MLX engine. Excludes remote hosts, Bionic workflows and external tools. · Not established · Proprietary app terms; bundled engines and model weights have separate licensesRevision 2026-09-15.1 · unreviewedNeeds recheck · recheck 2026-10-150 attestations · checked 2026-09-15

What we do not know yet · 3 open 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.

Applies to: Living documentation accessed 2026-09-15; app and installed engine versions are not pinned. · Local LM Studio app and server; pin the separately installed llama.cpp or MLX engine. Excludes remote hosts, Bionic workflows and external tools.

Applicability, 2 recheck triggers & verification plan

Applicability

Living documentation accessed 2026-09-15; app and installed engine versions are not pinned.

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

Recheck when

Runtime, bundled engine, backend, model format or license changes.
Documentation changes affecting the cited configuration.

Needs recheck · due 2026-10-15

Verification plan

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.

Provenance & review

Testedknowhow model runtime research

Commissioned by a Nimbalyst maintainer. Documentation synthesis; no independent review or product execution.

Revision 2026-09-15.1 · unreviewed · checked 2026-09-15

0 attestations · Content: Unlicensed prototype; redistribution decision pending

Capability claims · 10 / 14 sourced

Standing condition: these are documentation claims at the source capture date, with outcome “claimed”; no runtime execution is recorded. Dossier applicability and limitations apply throughout. Expand a row for its statement, specific scope and contradictions. Numbered citations resolve to the source locator and capture date below. Missing evidence means Unknown, not No. Sources are unpinned unless marked “Pinned”; this marks source stability, not stronger support or runtime verification. Reuse counts refer to claims in the full dossier; repeated citations do not represent independent sources.

Yes Documented within scope Partial Limited form of the feature No Explicit evidence of absence Unknown No evidence recorded. These are support assessments, not quality scores or runtime verification.

Execution & hardware

Local inferenceYes

Explore Local inference →

Local chat and server operation can work offline.

Scope: Download models and runtimes first; discovery, downloads and app updates need connectivity.

[2]

Apple Silicon accelerationYes

Explore Apple Silicon acceleration →

Supports Apple Silicon Macs and the MLX engine.

Scope: Check the documented macOS and hardware requirements; Intel Mac support is not implied.

[1]

Model formats

GGUF modelsYes

Explore GGUF models →

Runs supported GGUF models with its llama.cpp engine.

Scope: Engine version is independently managed; supported model architectures only.

[1]

MLX modelsYes

Explore MLX models →

Runs supported MLX models on Apple Silicon.

Scope: MLX engine only; does not imply GGUF and MLX artifacts are interchangeable.

[1]

Serving

Local HTTP serverYes

Explore Local HTTP server →

Provides a local inference server.

Scope: Local inference with preloaded models; remote tools are excluded.

[2]

OpenAI-style chat endpointYes

Explore OpenAI-style chat endpoint →

Exposes an OpenAI-style chat-completions endpoint.

Scope: Documented request fields only; no complete OpenAI API parity claim.

[6]

Streaming generationYes

Explore Streaming generation →

Supports streaming in the chat-completions API.

Scope: stream request parameter; compatible local model and engine.

[6]

JSON schema outputYes

Explore JSON schema output →

Accepts JSON schema constraints for generation.

Scope: GGUF uses llama.cpp grammars and MLX uses Outlines; reliability varies by model.

[5]

Concurrent inferencePartial

Explore Concurrent inference →

Documents parallel requests for the llama.cpp engine; MLX support is listed as forthcoming.

Scope: Partial across the target engines: llama.cpp continuous batching only at capture date; configure Max Concurrent Predictions.

[4]

Runtime controls

Speculative decodingYes

Explore Speculative decoding →

Provides draft-model speculative decoding.

Scope: Main and draft vocabularies must match; added resource use may slow generation.

[7]

Unknown · 4 capabilities without evidence

Interface images & local attachments

Screenshots & attachments

Image index

Official project screenshots and your own reference images. Images illustrate a UI; they do not verify feature behavior. Uploads stay in this browser.

No screenshots gathered yet.