---
title: "Local AI apps & runtimes | Ethical Stack"
url: https://ethicalstack.ai/compare/local-ai/
catalog_version: f6baff2119d0e9158520da7fbe4232011dac79f25bd08757436d7a1dbd593db2
---

# Local AI apps & runtimes

Run downloaded models on your own hardware. Check cloud fallback, telemetry and model rights.

5 entries. Each finding links to the profile evidence, scope, confidence, recorded review dates and unknowns. Task-specific findings and rankings match this comparison on the website.

| Tool | Published overall | Energy practices | Training data | Your data & privacy | Openness | Worker protections | Military ties | BDS targets |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [Ollama](https://ethicalstack.ai/products/ollama/) | 5.6/10; 5/6 rated | [2/10](https://ethicalstack.ai/products/ollama/#energy) | [N/A](https://ethicalstack.ai/products/ollama/#training-rights) | [9/10](https://ethicalstack.ai/products/ollama/#privacy) | [9/10](https://ethicalstack.ai/products/ollama/#openness) | [1/10](https://ethicalstack.ai/products/ollama/#labour) | [7/10](https://ethicalstack.ai/products/ollama/#military-contracts) | [Not listed](https://ethicalstack.ai/products/ollama/#israel-palestine) |
| [Kokoro-82M](https://ethicalstack.ai/models/kokoro-82m/) | 5.5/10; 6/6 rated | [4/10](https://ethicalstack.ai/models/kokoro-82m/#energy) | [5/10](https://ethicalstack.ai/models/kokoro-82m/#training-rights) | [8/10](https://ethicalstack.ai/models/kokoro-82m/#privacy) | [8/10](https://ethicalstack.ai/models/kokoro-82m/#openness) | [1/10](https://ethicalstack.ai/models/kokoro-82m/#labour) | [7/10](https://ethicalstack.ai/models/kokoro-82m/#military-contracts) | [Not listed](https://ethicalstack.ai/models/kokoro-82m/#israel-palestine) |
| [Whisper speech recognition](https://ethicalstack.ai/models/openai-whisper/) | 4.8/10; 6/6 rated | [4/10](https://ethicalstack.ai/models/openai-whisper/#energy) | [2/10](https://ethicalstack.ai/models/openai-whisper/#training-rights) | [8/10](https://ethicalstack.ai/models/openai-whisper/#privacy) | [8/10](https://ethicalstack.ai/models/openai-whisper/#openness) | [4/10](https://ethicalstack.ai/models/openai-whisper/#labour) | [3/10](https://ethicalstack.ai/models/openai-whisper/#military-contracts) | [Not listed](https://ethicalstack.ai/models/openai-whisper/#israel-palestine) |
| [LM Studio](https://ethicalstack.ai/products/lm-studio/) | 4.8/10; 5/6 rated | [2/10](https://ethicalstack.ai/products/lm-studio/#energy) | [N/A](https://ethicalstack.ai/products/lm-studio/#training-rights) | [9/10](https://ethicalstack.ai/products/lm-studio/#privacy) | [5/10](https://ethicalstack.ai/products/lm-studio/#openness) | [1/10](https://ethicalstack.ai/products/lm-studio/#labour) | [7/10](https://ethicalstack.ai/products/lm-studio/#military-contracts) | [Not listed](https://ethicalstack.ai/products/lm-studio/#israel-palestine) |
| [Liquid Apollo](https://ethicalstack.ai/products/liquid-apollo/) | 3.6/10; 5/6 rated | [4/10](https://ethicalstack.ai/products/liquid-apollo/#energy) | [N/A](https://ethicalstack.ai/products/liquid-apollo/#training-rights) | [8/10](https://ethicalstack.ai/products/liquid-apollo/#privacy) | [2/10](https://ethicalstack.ai/products/liquid-apollo/#openness) | [2/10](https://ethicalstack.ai/products/liquid-apollo/#labour) | [2/10](https://ethicalstack.ai/products/liquid-apollo/#military-contracts) | [Not listed](https://ethicalstack.ai/products/liquid-apollo/#israel-palestine) |

## How to read the scores

- Assessments are provisional editorial judgments. Cite the profile and the underlying sources, and retain confidence, scope and unknowns.
- Unknown, not-applicable and model-dependent are different states. Missing evidence does not establish good or bad conduct.
- Company-level evidence does not establish use of a particular product or model. Account plan, model, host and route can change an assessment.
- Energy scores describe documented practices and transparency, not measured request emissions. Zero component points can mean an evidence gap.
- Published overall scores require at least four of six numerical dimensions. Preserve coverage and BDS adjustments; BDS itself is categorical.
- No named BDS target found is limited to the reviewed campaign sources and is not approval. Personalized priorities do not change the published overall score.
- Review and source-check dates describe the research, not this deployment. Fetch current primary sources when the decision requires current verification.

[Methodology](https://ethicalstack.ai/methodology/) · [Query selected findings](https://ethicalstack.ai/agents/index.md)