Skip to content
ModelCap

UI TARS 7B SFT

Official publisher releaseOpen weights

ByteDance Seed

UI TARS 7B SFT is a language model from ByteDance Seed. Its rank belongs to UI TARS 7B DPO, the model this route serves. Its weights are openly downloadable.

Figures as of 24 Oct 2026, 19:29 UTC · download the public dataset · methodology

ModelCap Index
See primary model · UI TARS 7B DPO
Route-specific operations remain below
Market Gravity
8.0Decreased by 0.1
Secondary market signal

This separately configured or accelerated route is reviewed as the same underlying model identity as UI TARS 7B DPO. That canonical product owns rank and capability evidence; pricing, providers and other operational differences remain route-specific below.

OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.

Input
Self-hosted
weights only · no listed API price
Output
Self-hosted
weights only · no listed API price
Context
—
tokens
Providers
0
endpoints

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

Reported evaluation leads (27)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. Rows marked as used were laddered against independently measured peers inside the launch-card channel of this model's modeled placement, with the replay-measured optimism haircut applied; the others played no part.

Dataset / taskMetricValueRevisionProvenance
likaixin/ScreenSpot-Pro
overall
—35.7
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
android_studio_macos
—21.2
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
autocad_windows
—8.8
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
blender_windows
—39.4
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
davinci_macos
—31.8
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
eviews_windows
—84
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
excel_macos
—31.2
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
fruitloops_windows
—28.1
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
illustrator_windows
—3.2
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
inventor_windows
—1.4
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
linux_common_linux
—28
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
macos_common_macos
—27.7
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
matlab_macos
—53.8
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
origin_windows
—24.2
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
photoshop_windows
—33.3
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
powerpoint_windows
—47.6
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
premiere_windows
—25
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
pycharm_macos
—37.2
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
quartus_windows
—28.9
Unpinned
not published
Reported
Not used in launch estimate
likaixin/ScreenSpot-Pro
solidworks_windows
—6.5
Unpinned
not published
Reported
Not used in launch estimate

Showing 20 of 27 rows.

Deployment readiness

Metadata index
47.9
partial · 52% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
8.0
Evaluation provenance
0.0

Not yet published: the base model it derives from, a current serving provider, measured provider uptime, published provider pricing, declared context and output limits, admitted benchmark results, results across several capability areas, results from more than one source, a confident match to its benchmark entries, pinned evaluation dataset versions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
8.0
OpenRouter weekly popularity
Not listed

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Market Gravity breakdown

Usage55%
0.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.4

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
8.7

Time since first public availability, on a six-month half-life.

Specification

Model ID
ByteDance-Seed/UI-TARS-7B-SFT
Declared output cap
Unknown

OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata

Inputs
Text, Image
Outputs
Text
Cached input tokens
Not offered
First seen on OpenRouter
20 Jan 2025

Capabilities

  • Not supported: Reasoning
  • Not supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
3434901a9dd0
Parameters
8.3B
Architecture
Qwen2VLForConditionalGeneration
Model type
qwen2_vl
Hugging Face downloads (30d)
1K
Downloads (all time)
102K
Likes
181
Repository updated
25 Jan 2025, 15:05 UTC