Updated 23 min ago · first seen 11 Sept 2026
model_01M294ZZ8V4Z04YJP1K97DVT3M
Overview
Identity
- Canonical model
- Yesidentity confidence: highOne 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
- None recorded
- API aliases
- qwen3-vl-4b-instructqwen3-vl-4b-reasoningIdentifiers under which providers and evaluators refer to this model.
- Folded evaluation variants
- 1Effort / 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 Apache-2.0; 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: Apache License 2.0 (permissive · SPDX Apache-2.0 · stated as “apache-2.0”)
dimensions marked null are unknown, not false
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium
- Status
Source:Artificial AnalysisT2observed 14 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium
Architecture
- Architecture
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium
- Model type
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium
- Parameters
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium
- Weights dtype
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium
- File size
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium
- Library name
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium
- Pipeline tag
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium
- Hugging Face repo
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium
Capabilities
Modalities
- Modalities
- imagetext
- Input
- imagetext
- Output
- text
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
No
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:Artificial AnalysisT2observed 14 h agomedium
Benchmarks28
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. 28 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 →
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.
Lineage
Open in Graph →- descendant: GELab-Zero-4B-preview
Versions & Artifacts0
Version history
Context windowfirst observation only
11 Sept 2026current
Licensefirst observation only
11 Sept 2026current
Opennessfirst observation only
11 Sept 2026current
Parametersfirst observation only
11 Sept 2026current
Statusfirst observation only
11 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.
Papers4
- arXiv:2505.09388Active35
- arXiv:2502.13923Active35
- arXiv:2409.12191Active35
- arXiv:2308.12966Active35
Timeline14
Full timeline →Qwen3-VL-4B-Instruct scores 0% on Terminal-Bench
artificial_analysisQwen3-VL-4B-Instruct scores 23.39% on τ²-bench
artificial_analysisQwen3-VL-4B-Instruct scores 43.87% on MMMU-Pro
artificial_analysisQwen3-VL-4B-Instruct scores 31.84% on IFBench
artificial_analysisQwen3-VL-4B-Instruct scores 3.61% on Humanity's Last Exam
artificial_analysisQwen3-VL-4B-Instruct scores 37.07% on GPQA Diamond
artificial_analysisQwen3-VL-4B-Instruct scores 5.66 on Artificial Analysis Intelligence Index
artificial_analysisQwen3-VL-4B-Instruct scores 1.52% on Terminal-Bench
artificial_analysisQwen3-VL-4B-Instruct scores 15.5% on τ²-bench
artificial_analysisQwen3-VL-4B-Instruct scores 52.02% on MMMU-Pro
artificial_analysisQwen3-VL-4B-Instruct scores 36.6% on IFBench
artificial_analysisQwen3-VL-4B-Instruct scores 4.59% on Humanity's Last Exam
artificial_analysisQwen3-VL-4B-Instruct scores 49.39% on GPQA Diamond
artificial_analysisQwen3-VL-4B-Instruct scores 7.05 on Artificial Analysis Intelligence Index
artificial_analysis
Change history
Reasoningreasoning2
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
36
Source tiers
T236
Freshest observation
1 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 (63/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →