Ling 3.0 Flash VL
inclusionAIhuggingface.co/inclusionAI/Ling-3.0-flash-VL
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...
Updated 2 h ago · first seen 11 Sept 2026
model_01M294WVM80NWASNA5CWS68F1R
Overview
Identity
- Canonical model
- Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
- Official checkpoints
- official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
- Artifacts
- None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
- Provider deployments
- 1
- API aliases
- inclusionai/ling-3.0-flash-vlling-3-0-flash-vlIdentifiers under which providers and evaluators refer to this model.
- Folded evaluation variants
- 0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.
Openness
Open weights— weights downloadable under MIT; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.
Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.
Weights
Yes
Inference code
—
Training code
—
Training data
—
Dataset
—
Commercial use
Yes
Redistribution
Yes
Derivatives
Yes
Licence: MIT License (permissive · SPDX MIT)
dimensions marked null are unknown, not false
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Architecture
- Architecture
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Model type
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Parameters
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Weights dtype
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- File size
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Pipeline tag
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 d agomedium
- Hugging Face repo
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Capabilities
Modalities
- Modalities
- imagetextvideo
- Input
- imagetextvideo
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
- Max output
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Benchmarks14
Compare with another model →Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric
Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 14 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →
Providers & Pricing2
All offers in the price terminal →USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →
Price history
Output price · USD / 1M tokens 1 provider
- OpenRouter
- OpenRouter$0.18 → $011 Sept 2026
- OpenRouterfirst observed $0.1811 Sept 2026
Input price · USD / 1M tokens 1 provider
- OpenRouter
- OpenRouter$0.06 → $011 Sept 2026
- OpenRouterfirst observed $0.0611 Sept 2026
Hardware fit37
Assumptions (7)
- Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
- bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
- KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
- A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
- Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
- Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
- Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.
Versions & Artifacts0
Version history
Context window2 changes
11 Sept 2026→11 Sept 2026→12 Sept 2026current
Licensefirst observation only
12 Sept 2026current
Max outputfirst observation only
11 Sept 2026current
Opennessfirst observation only
11 Sept 2026current
Parametersfirst observation only
12 Sept 2026current
Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.
Artifacts 0
No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.
Timeline15
Full timeline →Ling 3.0 Flash VL on Artificial Analysis Intelligence Index: 24.77 → 24.97
24.77→24.97artificial_analysisLing 3.0 Flash VL: hf inference providers changed from ["novita"] to ["deepinfra", "novita"]
Hf inference providersnovita→deepinfra, novitahuggingfaceLing 3.0 Flash VL: modalities changed from ["image", "text"] to ["image", "text", "video"]
Modalitiesimage, text→image, text, videoopenrouterLing 3.0 Flash VL: modalities input changed from ["image", "text"] to ["image", "text", "video"]
Input modalitiesimage, text→image, text, videoopenrouterLing 3.0 Flash VL: release date changed from 2026-09-10 to 2026-09-04
Release date10 Sept 2026→4 Sept 2026huggingfaceLing 3.0 Flash VL: modalities changed from ["image", "text", "video"] to ["image", "text"]
Modalitiesimage, text, video→image, texthuggingfaceLing 3.0 Flash VL: modalities input changed from ["image", "text", "video"] to ["image", "text"]
Input modalitiesimage, text, video→image, texthuggingfaceLing 3.0 Flash VL scores 64.42% on Terminal-Bench
artificial_analysisLing 3.0 Flash VL scores 0% on Terminal-Bench
artificial_analysisLing 3.0 Flash VL scores 78.96% on MMMU-Pro
artificial_analysisLing 3.0 Flash VL scores 44.21% on SciCode
artificial_analysisLing 3.0 Flash VL scores 21.96% on Humanity's Last Exam
artificial_analysisLing 3.0 Flash VL scores 86.16% on GPQA Diamond
artificial_analysisLing 3.0 Flash VL scores 24.77 on Artificial Analysis Intelligence Index
artificial_analysisLing 3.0 Flash VL: context length changed from 262144 to 131072
Context window262.1K tokens→131.1K tokensopenrouter
Change history160
Viewing AI Atlas as of 9 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Ling 3.0 Flash VL was not yet in AI Atlas on 9 Sept 2026
Release daterelease_date2
Opennessopenness1
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Context windowcontext_length3
Max outputmax_output_tokens1
Modalitiesmodalities47
Input modalitiesmodalities_input47
Output modalitiesmodalities_output1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Model cardmodel_card_url1
Downloadsmetric.downloads4
Likesmetric.likes13
Aa context windowaa_context_window1
Aa opennessaa_openness1
Accessaccess1
Commercial use allowedcommercial_use_allowed1
Derivatives allowedderivatives_allowed1
Descriptiondescription1
Hf inference providershf_inference_providers2
Last modifiedlast_modified1
License keylicense_key1
License rawlicense_raw1
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second7
Downloads all timemetric.downloads_all_time4
Model typemodel_type1
Openrouter idopenrouter_id1
Openrouter listed atopenrouter_listed_at1
Reasoningreasoning1
Redistribution allowedredistribution_allowed1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Visionvision1
Weights availableweights_available1
Weights dtypeweights_dtype1
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Provenance
Attributed facts
40
Source tiers
T240
Freshest observation
2 h ago
Conflicts
None
Source documents 5
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (72/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →