agent · model serving

LM Studio

lmstudio.aievidence retrieved Aug 7, 2026 – Aug 20, 2026view as JSON all model serving entries 4 alternatives

Indexed12 or more fields evidenced; not yet scored by a human against the rubric

18 fields evidenced · 38 with no public information. Every value below links to the document it came from and the date we checked it.

1 of those are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist

1 of the evidenced values quotes wording our own later capture of the same page no longer contains. Marked below, awaiting an editor.

Also appears in

AI agents that support the Model Context Protocol

Trust gap

How this is scored

These scores are automated. A 1 or 2 counts how many fields this entry answers with a citation — not what those answers say. A 0 means every field for that dimension is recorded as undisclosed and none of the pages we captured mentions it. No one has scored this entry against the rubric yet.

Runtime governance

unscored

Are scope, spend, and authority enforced while the agent runs?

Audit trail

1/3 auto

Is there a tamper-evident record of what it actually did?

Scored from 1 evidenced field(s): audit_trail. Automated score; capped at 2 pending review.

Counts Audit trail, each cited below.

Compliance

unscored

Are compliance obligations attached per engagement?

Outcome settlement

unscored

Does payment depend on a verified result?

Insurance & indemnity

unscored

Can the deployment be insured, and is the customer indemnified?

Assurance

Insurance available: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Insurance carriers: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Coverage limits: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Indemnification: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Liability cap: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Audit trail: yes
“Every change is automatically saved, so you can work with your agent freely.”
lmstudio.ai · checked Aug 7, 2026
Tamper-evident log: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Explainability: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Runtime governance: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Permission scopes: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Compliance certifications: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Regulatory alignment: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Outcome-based pricing: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Settlement mechanism: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Asset custody: no public information
lmstudio.ai · checked Aug 13, 2026 · source did not state this
Dispute process: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
SLA terms: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Evaluation coverage: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this

Agency

Autonomy level: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Human oversight: Requires permission prompts before destructive file-deletion actions
“Permission prompts for destructive file deletion operations.”
lmstudio.ai · checked Aug 20, 2026
Goal complexity: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Action space: Coding tasks, automations, and computer control
“Bionic also excels at coding tasks, automations, and computer control.”
lmstudio.ai · checked Aug 10, 2026
Operating environment: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Initiative: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this

Safety

Safety evaluations: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Red teaming: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Safety policy: Zero Data Retention (ZDR)
“Privacy is key to the LM Studio ethos. Our cloud services are Zero Data Retention (ZDR) across the board.”
lmstudio.ai · checked Aug 7, 2026
Usage restrictions: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Model or system card: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Incident reporting: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Third-party evaluations: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Data handling: Voice/audio data processed locally and never leaves the device; cloud services run Zero Data Retention (ZDR)
“Your voice and audio data is processed locally and never leaves your device.”
lmstudio.ai · checked Aug 10, 2026

Practicality

Pricing model: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Price point: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Availability: Available for direct download via a "Download LM Studio Bionic" button; no longer described on-page as an "initial preview" release.
“Download LM Studio Bionic”
lmstudio.ai · checked Aug 10, 2026
Deployment options: Local deployment; models downloaded and run directly within the app
“Download the latest local LLMs directly within the app and use them for simple chats or advanced agentic tasks.”
lmstudio.ai · checked Aug 10, 2026
Integrations: Integrates with Hugging Face for model card rendering
“Better Hugging Face model card rendering.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 17, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
lmstudio.ai · checked Aug 20, 2026
Supported regions: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Support model: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this

Foundation models

Base models: GLM 5.2, Kimi K3, DeepSeek V4 Pro
“run Bionic with the latest frontier open models such as GLM 5.2, Kimi K3, and DeepSeek V4 Pro.”
lmstudio.ai · checked Aug 7, 2026
Model provider: GLM 5.2, Kimi K3, DeepSeek V4 Pro
“run Bionic with the latest frontier open models such as GLM 5.2, Kimi K3, and DeepSeek V4 Pro.”
lmstudio.ai · checked Aug 7, 2026
Model swappable: yes
“Download the latest local LLMs directly within the app and use them for simple chats or advanced agentic tasks.”
lmstudio.ai · checked Aug 7, 2026
Open weights: Supports open-weight models (e.g. GLM 5.2, Kimi K3, DeepSeek V4 Pro, Muse Glimmer 30B under Apache 2.0)
“Bionic is LM Studio's agent for open models.”
lmstudio.ai · checked Aug 10, 2026
Fine-tuning: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Context window: not yet interpreted
“Automatic context sizing for local MLX models based on available memory.”
lmstudio.ai · checked Aug 20, 2026

Ecosystem

Protocols supported: Supports MCP (Model Context Protocol) servers, including OAuth authentication
“Clearer button to complete authentication for OAuth MCP servers.”
lmstudio.ai · checked Aug 20, 2026
Tool use: executes automations and computer control
“Bionic also excels at coding tasks, automations, and computer control.”
lmstudio.ai · checked Aug 7, 2026
Multi-agent: Supports subagents running within a session (multi-agent-style orchestration)
“More consistent progress indicators while tools and subagents are running.”
lmstudio.ai · checked Aug 20, 2026
API access: Provides a local API server with start/stop controls in settings
“Fixed local API server start/stop errors not appearing in settings.”
lmstudio.ai · checked Aug 20, 2026
Open source: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Marketplace presence: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this

Impact

User base: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Deployment scale: no public information
lmstudio.ai · checked Aug 10, 2026 · source did not state this
Target sectors: creativity, work, and code
“Bionic is LM Studio's agent for open models. Natively local. Built for creativity, work, and code.”
lmstudio.ai · checked Aug 10, 2026
High-risk domains: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this
Documented incidents: no public information
lmstudio.ai · checked Aug 7, 2026 · source did not state this

Compared with

Side-by-side on the fields where LM Studio and the other entry are both on record and actually differ.