Skip to content
AI Atlas
ModelActiveOpen weights

FLUX.2-dev

Black Forest Labsfamily · FLUXhuggingface.co/black-forest-labs/FLUX.2-dev

Open in Graph
data quality54

Updated 5 h ago · first seen 11 Sept 2026

model_01M294XNWQFG365NKWWDT9BX9R

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
1 quantization0 official · 1 third-partySeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
None recorded
API aliases
NoneIdentifiers 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 Other; 7 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

    —

  • Redistribution

    —

  • Derivatives

    —

Licence: Other (unclassified licence) (unknown · stated as “other”)

dimensions marked null are unknown, not false

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Architecture

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 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 15 h agomedium

Hugging Face repo

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Capabilities

Modalities

Modalities unavailable.

Capabilities

  • Tool calling

    Unavailable

  • Structured output

    Unavailable

  • Reasoning

    Unavailable

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

No capability flags have been observed from a source yet — we do not infer them.

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Hardware fit37

Estimated

36 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—19.0 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—19.0 GB est.Yes
Apple M2 Ultra4bit—19.0 GB est.Yes
Apple M1 Ultra4bit—19.0 GB est.Yes
Apple M3 Max4bit—19.0 GB est.Yes
Apple M4 Max4bit—19.0 GB est.Yes
Mac Studio (Apple M5 Max)4bit—19.0 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—19.0 GB est.Yes
Apple M2 Max4bit—19.0 GB est.Yes
Apple M1 Max4bit—19.0 GB est.Yes
Apple M4 Pro4bit—19.0 GB est.Yes
Mac mini (Apple M5 Pro)4bit—19.0 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—19.0 GB est.Yes
Apple M3 Pro4bit—19.0 GB est.Yes
Apple M1 Pro4bit—19.0 GB est.Yes
Apple M2 Pro4bit—19.0 GB est.Yes
Apple M44bit—19.0 GB est.Yes
iMac (Apple M4)4bit—19.0 GB est.Yes
Mac mini (Apple M6)4bit—19.0 GB est.Yes
MacBook Air (Apple M5)4bit—19.0 GB est.Yes
MacBook Pro (Apple M5)4bit—19.0 GB est.Yes
Apple M24bit—19.0 GB est.Yes
Apple M34bit—19.0 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB19.0 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB19.0 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB19.0 GB est.Yes
NVIDIA A100 80GB4bit80 GB19.0 GB est.Yes
NVIDIA H100 SXM4bit80 GB19.0 GB est.Yes
NVIDIA H100 NVL4bit94 GB19.0 GB est.Yes
NVIDIA DGX Spark4bit128 GB19.0 GB est.Yes
NVIDIA H2004bit141 GB19.0 GB est.Yes
NVIDIA H200 NVL4bit141 GB19.0 GB est.Yes
NVIDIA B2004bit180 GB19.0 GB est.Yes
AMD Instinct MI300X4bit192 GB19.0 GB est.Yes
AMD Instinct MI325X4bit256 GB19.0 GB est.Yes
NVIDIA DGX B2004bit1,440 GB19.0 GB est.Yes
Apple M14bit—19.0 GB est.No
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 →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
DESCENDANTS 0 · ARTIFACTS1 quantizationartifacts · collapsed1 quantization — artifacts · collapsedFLUX.2-dev32.2B params · this modelFLUX.2-dev — 32.2B params · this model

    Versions & Artifacts1

    Version history

    Openness1 change

    11 Sept 2026→12 Sept 2026current

    Licensefirst observation only

    11 Sept 2026current

    Parametersfirst 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 1

    quantization 1

    Change history20

    Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

    Viewing AI Atlas as of 14 Jun 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

    Back to today →

    FLUX.2-dev was not yet in AI Atlas on 14 Jun 2026

    First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.
    20 claims · 19 properties

    Release daterelease_date1

    Claim history for Release date
    ValueValid from → toStatusSourceConfidenceExtractor
    22 Nov 2025 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Opennessopenness2

    Claim history for Openness
    ValueValid from → toStatusSourceConfidenceExtractor
    open-weights → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived
    restricted → supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Licenselicense1

    Claim history for License
    ValueValid from → toStatusSourceConfidenceExtractor
    Other → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Parametersparameter_count1

    Claim history for Parameters
    ValueValid from → toStatusSourceConfidenceExtractor
    32.2B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Languageslanguages1

    Claim history for Languages
    ValueValid from → toStatusSourceConfidenceExtractor
    en → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    File sizefile_size_gb1

    Claim history for File size
    ValueValid from → toStatusSourceConfidenceExtractor
    64.5 GB → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Hugging Face repohf_repo1

    Claim history for Hugging Face repo
    ValueValid from → toStatusSourceConfidenceExtractor
    black-forest-labs/FLUX.2-dev → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Pipeline tagpipeline_tag1

    Claim history for Pipeline tag
    ValueValid from → toStatusSourceConfidenceExtractor
    image-to-image → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Model cardmodel_card_url1

    Claim history for Model card
    ValueValid from → toStatusSourceConfidenceExtractor
    https://huggingface.co/black-forest-labs/FLUX.2-dev → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Downloadsmetric.downloads1

    Claim history for Downloads
    ValueValid from → toStatusSourceConfidenceExtractor
    398,947 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Likesmetric.likes1

    Claim history for Likes
    ValueValid from → toStatusSourceConfidenceExtractor
    2,214 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Gatedgated1

    Claim history for Gated
    ValueValid from → toStatusSourceConfidenceExtractor
    auto → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Hf inference providershf_inference_providers1

    Claim history for Hf inference providers
    ValueValid from → toStatusSourceConfidenceExtractor
    fal-ai, replicate, together, wavespeed → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Last modifiedlast_modified1

    Claim history for Last modified
    ValueValid from → toStatusSourceConfidenceExtractor
    2026-02-17T15:56:06+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Library namelibrary_name1

    Claim history for Library name
    ValueValid from → toStatusSourceConfidenceExtractor
    diffusers → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Downloads all timemetric.downloads_all_time1

    Claim history for Downloads all time
    ValueValid from → toStatusSourceConfidenceExtractor
    4,566,656 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Tagstags1

    Claim history for Tags
    ValueValid from → toStatusSourceConfidenceExtractor
    diffusers, safetensors, image-generation, image-editing, flux, diffusion-single-file, image-to-image, en → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Weights availableweights_available1

    Claim history for Weights available
    ValueValid from → toStatusSourceConfidenceExtractor
    Yes → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

    Weights dtypeweights_dtype1

    Claim history for Weights dtype
    ValueValid from → toStatusSourceConfidenceExtractor
    BF16 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    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

    21

    Source tiers

    T221

    Freshest observation

    5 h ago

    Conflicts

    None

    Source documents 2

    Source documents
    SourceDocumentTypeTierLast observedSnapshots
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=black-forest-labs&p=0&sort=downloads listingT2· Quality secondary45 min ago8
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/black-forest-labs/FLUX.2-dev model_pageT2· Quality secondary9 h ago5

    Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

    Data quality (54/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →