Skip to content
AI Atlas
ModelActiveOpen weights

medgemma-4b-it

Googlehuggingface.co/google/medgemma-4b-it

Open in Graph

Updated 1 h ago · first seen 12 Sept 2026

model_01M2AS5H97YF0BQVZZMHD4TZVW

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
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)

dimensions marked null are unknown, not false

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Hugging Face repo

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Capabilities

Modalities

Modalities
imagetext
Input
imagetext
Output
text

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.

No structured attributes yet.

Hardware fit37

Estimated

37 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—3.0 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—3.0 GB est.Yes
Apple M2 Ultra4bit—3.0 GB est.Yes
Apple M1 Ultra4bit—3.0 GB est.Yes
Apple M3 Max4bit—3.0 GB est.Yes
Apple M4 Max4bit—3.0 GB est.Yes
Mac Studio (Apple M5 Max)4bit—3.0 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—3.0 GB est.Yes
Apple M2 Max4bit—3.0 GB est.Yes
Apple M1 Max4bit—3.0 GB est.Yes
Apple M4 Pro4bit—3.0 GB est.Yes
Mac mini (Apple M5 Pro)4bit—3.0 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—3.0 GB est.Yes
Apple M3 Pro4bit—3.0 GB est.Yes
Apple M1 Pro4bit—3.0 GB est.Yes
Apple M2 Pro4bit—3.0 GB est.Yes
Apple M44bit—3.0 GB est.Yes
iMac (Apple M4)4bit—3.0 GB est.Yes
Mac mini (Apple M6)4bit—3.0 GB est.Yes
MacBook Air (Apple M5)4bit—3.0 GB est.Yes
MacBook Pro (Apple M5)4bit—3.0 GB est.Yes
Apple M24bit—3.0 GB est.Yes
Apple M34bit—3.0 GB est.Yes
Apple M14bit—3.0 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB3.0 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB3.0 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB3.0 GB est.Yes
NVIDIA A100 80GB4bit80 GB3.0 GB est.Yes
NVIDIA H100 SXM4bit80 GB3.0 GB est.Yes
NVIDIA H100 NVL4bit94 GB3.0 GB est.Yes
NVIDIA DGX Spark4bit128 GB3.0 GB est.Yes
NVIDIA H2004bit141 GB3.0 GB est.Yes
NVIDIA H200 NVL4bit141 GB3.0 GB est.Yes
NVIDIA B2004bit180 GB3.0 GB est.Yes
AMD Instinct MI300X4bit192 GB3.0 GB est.Yes
AMD Instinct MI325X4bit256 GB3.0 GB est.Yes
NVIDIA DGX B2004bit1,440 GB3.0 GB est.Yes
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.
ANCESTORS 1medgemma-4b-ptGooglemedgemma-4b-pt — Googlemedgemma-4b-it4.3B params · this modelmedgemma-4b-it — 4.3B params · this model

Versions & Artifacts0

Version history

Licensefirst observation only

12 Sept 2026current

Opennessfirst observation only

12 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.

Papers11

Timeline1

Full timeline →

Change history28

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
28 claims · 28 properties

Release daterelease_date1

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

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentHugging 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

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
Gemma3ForConditionalGeneration → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
4.3B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
image, text → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
image, text → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Base modelbase_model1

Claim history for Base model
ValueValid from → toStatusSourceConfidenceExtractor
google/medgemma-4b-pt → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

File sizefile_size_gb1

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

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
google/medgemma-4b-it → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Pipeline tagpipeline_tag1

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

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/google/medgemma-4b-it → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
1,064,703 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes1

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
1,052 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Accessaccess1

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

Gated modegated_mode1

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

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2025-10-28T17:24:49+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Library namelibrary_name1

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

License keylicense_key1

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

License namelicense_name1

Claim history for License name
ValueValid from → toStatusSourceConfidenceExtractor
health-ai-developer-foundations → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

License rawlicense_raw1

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

License urllicense_url1

Claim history for License url
ValueValid from → toStatusSourceConfidenceExtractor
https://developers.google.com/health-ai-developer-foundations/terms → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
5,424,574 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
gemma3 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
chest-x-ray, clinical-reasoning, dermatology, gemma3, image-text-to-text, medical, ophthalmology, pathology, radiology, safetensors, transformers → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Weights availableweights_available1

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

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

28

Source tiers

T228

Freshest observation

2 h ago

Conflicts

None

Source documents 2

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/google/medgemma-4b-it model_pageT2· Quality secondary2 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=google&p=0&sort=downloads listingT2· Quality secondary2 h ago8

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

Data quality (not computed) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →