Open Model WeightsXIAOMI RESEARCH · FIELD VERIFIED
Primary sources last checked on 4 Nov 2026. Verification freshness is tracked separately from factual change, and unknown values remain explicit rather than inferred.
CONCEPTUAL MODEL BRIEF · ORIGINAL ILLUSTRATION
A topic-specific editorial visual, not an independent model performance measurement.MODEL INTELLIGENCE · SOURCE-FIRST
Open Model Weights records Xiaomi-OCR-0 as a 0.873439B-parameter document images and text → text open-weight model in the Xiaomi OCR family, with Xiaomi Research listed as the developer. The checked source repository provides 1 recognized weight artifacts, format evidence for Safetensors and a verified context window of 262,144 tokens. Values that are not evidenced in the checked sources remain explicitly undisclosed or unknown.
The repository declares apache-2.0. Commercial use allowed under apache-2.0 conditions. Open Model Weights reports the checked license evidence and classification; this is not legal advice.
The checked sources declare Qwen/Qwen3.5-0.8B-Base as lineage evidence. Training recipe status: training-described-in-model-card; data disclosure status: dataset-metadata-declared.
+ Save to my shortlistMonitor changes →Local browser monitoring · no background email alerts
DIRECT ANSWER · FEATURED MODEL BRIEFING
Source-grounded editorial layer · reviewed 2026-11-04
Xiaomi-OCR-0 is a compact document-oriented vision-language model for recognizing text, understanding layouts and answering document questions. Its public source Safetensors and Apache-2.0 repository declaration were independently checked. Open Model Weights independently inspected the exact repository revision, listed weight artifacts and declared license; it has not run the model or reproduced publisher benchmark results. The source verifier found a model-card and repository license declaration, not a separately checked standard license file.
WHY IT MATTERS
A 0.8B OCR-specialist derived from a Qwen3.5-0.8B base for parsing tables, formulas and scanned pages. The exact configuration and operational assumptions should be checked against the source model card rather than assumed from the name alone.
Apache-2.0 is declared in model metadata; no separately checked standard LICENSE file was found by the source verifier. The exact configuration and operational assumptions should be checked against the source model card rather than assumed from the name alone.
Xiaomi's strong published OCR benchmark scores are manufacturer claims, not measurements by Open Model Weights. The exact configuration and operational assumptions should be checked against the source model card rather than assumed from the name alone.
MODEL-SELECTION VIEW
A 0.8B OCR-specialist derived from a Qwen3.5-0.8B base for parsing tables, formulas and scanned pages. The exact configuration and operational assumptions should be checked against the source model card rather than assumed from the name alone.
The repository xiaomi-research/Xiaomi-OCR-0 was checked at commit bbd8cf8d21f256b3644b44cb860f3a7cecb93c30. This evidence establishes a real published weight distribution, but no independent user task or hardware benchmark was performed by Open Model Weights.
The official source lists public Safetensors and model configuration, distinct from third-party GGUF conversions. The exact configuration and operational assumptions should be checked against the source model card rather than assumed from the name alone.
The published weight manifest and associated processor or tokenizer components must be pinned to bbd8cf8d21f256b3644b44cb860f3a7cecb93c30 to avoid silently mixing revisions. Converted quantizations and separately licensed dependencies are outside an automatic equivalence guarantee.
Apache-2.0 is declared in model metadata; no separately checked standard LICENSE file was found by the source verifier. The exact configuration and operational assumptions should be checked against the source model card rather than assumed from the name alone.
The exact repository license identifier is apache-2.0. Commercial-use clearance is recorded only as supported by checked source metadata and text; third-party assets, deployment software, encoders and data sources retain their own terms.
Xiaomi's strong published OCR benchmark scores are manufacturer claims, not measurements by Open Model Weights. The exact configuration and operational assumptions should be checked against the source model card rather than assumed from the name alone.
Publisher benchmarks are useful context but depend on their chosen prompts, hardware, code revision and comparison conditions. Open Model Weights does not claim to have reproduced any reported ranking or speed figure.
End-to-end OCR depends on page imaging, resolution, decoding and post-processing beyond model weight size. The exact configuration and operational assumptions should be checked against the source model card rather than assumed from the name alone.
Actual deployment of Xiaomi-OCR-0 0.8B requires consistent model code, configuration, runtime, security permissions and memory budget. Do not infer general usability solely from public downloads or parameter count.
IMPLEMENTATION & EVALUATION
Reproducible operator checklist; these steps are not claims of an OMW model run.
A named model does not guarantee identical checkpoint revisions.
Record 40-character SHA, original file names, configuration and tokenizer/processor versions.
Unpinned revisions can silently change weights or usage requirements.
A specialist checkpoint can fail outside the publisher's demonstrated conditions.
Document actual prompt templates, modality preprocessing, inference backend and compatible software versions.
Using unsupported serving backends can invalidate comparisons.
Model card labels and code licenses are not automatically permission for every deployed use.
Check exact weight terms, notices, tool permissions, data privacy and runtime isolation.
Restricted weight rights or unsafe action tools can make a deployment unsuitable.
Vendor benchmark figures are useful evidence, but are not OMW-run observations.
Pre-register held-out tasks and compare baseline checkpoint, hardware, quality, memory and error rates.
Attributing first-party results to independent inference would mislead readers.
Proposed tests, not OMW benchmark results. Read the official model card at the pinned source revision ↗ Inspect OMW field evidence ↗
PRIMARY & INDEPENDENT SOURCES
FAQ
A 0.8B OCR-specialist derived from a Qwen3.5-0.8B base for parsing tables, formulas and scanned pages. The official checkpoint must be distinguished from third-party conversions and derivatives.
Yes. Exact public Safetensors were found in xiaomi-research/Xiaomi-OCR-0 at the pinned source revision. External dependencies may have different access conditions.
Apache-2.0 is declared in model metadata; no separately checked standard LICENSE file was found by the source verifier. The source verifier only records evidenced permissions and does not issue legal clearance.
Xiaomi's strong published OCR benchmark scores are manufacturer claims, not measurements by Open Model Weights. OMW has not run a separate evaluation.
End-to-end OCR depends on page imaging, resolution, decoding and post-processing beyond model weight size. Operators should verify compatible software and isolate external tools.
Compare against Surya 2.5 and MiniCPM-OCR using identical held-out pages, exact rights and one test harness. No unperformed independent speed or quality measurement is claimed.
03 · PRACTICAL TECHNICAL PROFILE
Inspect weight-memory estimates, model lineage and runtime evidence separately from promotional or untested performance claims.
DEPLOYMENT PROFILE
These bars visualize weight-only decimal-GB estimates. They exclude KV cache, activations, runtime overhead, optimizer state and sharding.
LICENSE & USE
Commercial use allowed under apache-2.0 conditions
This section summarizes the checked repository evidence. It is not legal advice.
LINEAGE & PROVENANCE
Open Model Weights does not infer a hidden base model or training corpus when the checked sources do not declare one.
RUNTIME SIGNALS
Declared and model-card-mentioned runtimes are discovery signals. They are not treated as Open Model Weights runtime tests unless explicitly measured.
EVIDENCE TRAIL
This is where the article remains auditable: source links on one side, the registry's observed change history on the other.
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
04 · EVIDENCE AND UPDATES
Inspect dated source checks and any differences between published claims and the evidence; these checks are not independent model benchmarks.
FRESHNESS & VERIFICATION
A verification check does not pretend the model changed. Open Model Weights updates the verification date after a real primary-source check, while factual-update dates move only when retained source evidence changes.
CONFLICT INTELLIGENCE
05 · SOURCE RECORD
Full repository-level attributes, licensing, format details and provenance are available below without hiding or rewriting the original data.
01 · WEIGHTS
02 · LICENSE
Classification describes the checked license terms; it is not legal advice.
03 · HARDWARE
Weight-only decimal-GB estimate from total parameter count; excludes KV cache, activations, runtime overhead, optimizer state and sharding.
04 · FORMATS
“Not observed” means no matching repository artifact/name/dtype signal was found; it does not prove no third-party conversion exists.
05 · LINEAGE
06 · TRAINING ASSETS
07 · RUNTIME SUPPORT
Open Model Weights separates model-repository evidence from external runtime-release evidence. An external support statement does not change the official model repository's weight formats and does not imply an Open Model Weights inference benchmark.
08 · SOURCES
09 · VERIFICATION HISTORY
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.