Skip to content
ModelCap

olmOCR 2 7B 1025 FP8

Official build · attached, unrankedOpen weights

Allen Institute·allenai/olmOCR-2-7B-1025-FP8

olmOCR 2 7B 1025 FP8 weight access is open weights, from ModelCap classification of published repository metadata as of 22 Sept 2026, 03:10 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index
See primary model · olmOCR 2 7B 1025
This release is visible for discovery, not ranked as a peer model
Market Gravity
14.8
Secondary market signal

This separately configured or accelerated route is reviewed as the same underlying model identity as olmOCR 2 7B 1025. 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
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

Reported evaluation leads (9)

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
allenai/olmOCR-bench
overall
—82.4
Unpinned
not published
Reported
Not used in launch estimate
allenai/olmOCR-bench
arxiv_math
—83
Unpinned
not published
Reported
Not used in launch estimate
allenai/olmOCR-bench
old_scans_math
—82.3
Unpinned
not published
Reported
Not used in launch estimate
allenai/olmOCR-bench
table_tests
—84.9
Unpinned
not published
Reported
Not used in launch estimate
allenai/olmOCR-bench
old_scans
—47.7
Unpinned
not published
Reported
Not used in launch estimate
allenai/olmOCR-bench
headers_footers
—96.1
Unpinned
not published
Reported
Not used in launch estimate
allenai/olmOCR-bench
multi_column
—83.7
Unpinned
not published
Reported
Not used in launch estimate
allenai/olmOCR-bench
long_tiny_text
—81.9
Unpinned
not published
Reported
Not used in launch estimate
allenai/olmOCR-bench
baseline
—99.7
Unpinned
not published
Reported
Not used in launch estimate

Other versions (3)

Deployment readiness

Metadata index
52.4
partial · 56% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
8.0
Evaluation provenance
0.0

Missing: deployability.independent-provider-records, deployability.measured-provider-uptime, deployability.published-provider-pricing, deployability.declared-capacity, evaluationProvenance.admitted-evaluation-observations, evaluationProvenance.capability-family-breadth, evaluationProvenance.evaluation-source-diversity, evaluationProvenance.identity-and-source-confidence, evaluationProvenance.evaluation-dataset-revisions.

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

Market activity

Venue coverage
Market Gravity
14.8
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%
89.7

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

Freshness5%
26.3

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

Specification

Context window
— tokens
Max output
—
Inputs
Text, Image
Outputs
Text
Tokenizer
—
Cached input tokens
Not offered
First seen on OpenRouter
6 Oct 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
40bd7202494b
Parameters
8.3B
Architecture
Qwen2_5_VLForConditionalGeneration
Model type
qwen2_5_vl
Hugging Face downloads (30d)
149K
Downloads (all time)
5.2M
Likes
257
Repository
allenai/olmOCR-2-7B-1025-FP8
Repository updated
19 Feb 2026, 17:30 UTC
Base lineage
Qwen/Qwen2.5-VL-7B-Instruct