Packaged runtime / PRODUCT DOSSIER

Ollama (local runtime)

Local model runner and HTTP API, scoped with cloud features disabled.

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

Official website ↗Explore in graph →11 cited claims ↓

Local Ollama server with OLLAMA_NO_CLOUD=1 and preloaded local models; excludes Ollama Cloud and web search. · Open source · MIT runtime source; 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 · 2 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?

Applies to: Repository revision a43fad18b088095de20fbd7a8f0de50824cf5d27; living documentation separately dated. · Local Ollama server with OLLAMA_NO_CLOUD=1 and preloaded local models; excludes Ollama Cloud and web search.

Applicability, 2 recheck triggers & verification plan

Applicability

Repository revision a43fad18b088095de20fbd7a8f0de50824cf5d27; living documentation separately dated.

Local Ollama server with OLLAMA_NO_CLOUD=1 and preloaded local models; excludes Ollama Cloud and web search.

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 · 11 / 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 →

Runs local models with cloud features disabled.

Scope: Set OLLAMA_NO_CLOUD=1 and restart; prefetch model files separately.

[2]

Apple Silicon accelerationYes

Explore Apple Silicon acceleration →

Supports Apple GPU acceleration through Metal.

Scope: Supported Apple hardware; actual memory fit unmeasured.

[3]

CPU inferenceYes

Explore CPU inference →

Documents CPU execution and GPU offload modes.

Scope: Backend placement can be inspected using ollama ps.

[2]

NVIDIA accelerationYes

Explore NVIDIA acceleration →

Supports NVIDIA GPUs within documented driver and compute requirements.

Scope: Check the hardware compatibility list for the chosen GPU.

[3]

Model formats

GGUF modelsYes

Explore GGUF models →

Imports local GGUF model files through a Modelfile.

Scope: Supported model architectures; import does not quantize the GGUF file.

[4]

Quantized weightsYes

Explore Quantized weights →

Can load previously quantized GGUF models.

Scope: Prepare quantization before GGUF import; no quality equivalence asserted.

[4]

Serving

Local HTTP serverYes

Explore Local HTTP server →

Exposes a local HTTP API.

Scope: Default bind is 127.0.0.1:11434; changing it affects network exposure.

[2]

OpenAI-style chat endpointYes

Explore OpenAI-style chat endpoint →

Supports a subset of OpenAI-compatible API fields and endpoints.

Scope: Only the documented endpoint and parameter subset.

[5]

Streaming generationYes

Explore Streaming generation →

Streams generated output as newline-delimited JSON.

Scope: Native API streaming protocol; separate from compatible API streaming.

[7]

JSON schema outputYes

Explore JSON schema output →

Accepts JSON schemas for structured generation.

Scope: Local runtime only; cited documentation excludes Ollama Cloud support.

[6]

Concurrent inferenceYes

Explore Concurrent inference →

Can process multiple requests to the same model in parallel.

Scope: Requires sufficient memory; parallel request count multiplies context memory and excess work queues.

[2]

Unknown · 3 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.

Sources · 7

[1]Ollama runtime license ↗Pinned2026-09-150 / 11 claims

repository · locator & rights

a43fad18b088095de20fbd7a8f0de50824cf5d27

MIT License