Skip to content
AI Atlas
ModelActive

Qwen2.5-Omni

Qwen Teamfamily · Qwen

Open in Graph
quality53

Updated 3 h ago · first seen 12 Sept 2026

model_01M29Y0B277Q2A3QK9FAXBWAAS

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Status

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Version

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Architecture

Architecture

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Parameters

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Capabilities

Modalities

Modalities
audioimagespeechtextvideo
Input
audioimagetextvideo
Output
speechtext

Capabilities

  • Tool calling

    Unavailable

  • Structured output

    Unavailable

  • Reasoning

    Unavailable

  • Vision

    Yes

    Qwen — official blog · T2

  • Audio

    Yes

    Qwen — official blog · T2

  • Fine-tuning available

    Unavailable

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—4.5 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—4.5 GB est.Yes
Apple M2 Ultra4bit—4.5 GB est.Yes
Apple M1 Ultra4bit—4.5 GB est.Yes
Apple M3 Max4bit—4.5 GB est.Yes
Apple M4 Max4bit—4.5 GB est.Yes
Mac Studio (Apple M5 Max)4bit—4.5 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—4.5 GB est.Yes
Apple M2 Max4bit—4.5 GB est.Yes
Apple M1 Max4bit—4.5 GB est.Yes
Apple M4 Pro4bit—4.5 GB est.Yes
Mac mini (Apple M5 Pro)4bit—4.5 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—4.5 GB est.Yes
Apple M3 Pro4bit—4.5 GB est.Yes
Apple M1 Pro4bit—4.5 GB est.Yes
Apple M2 Pro4bit—4.5 GB est.Yes
Apple M44bit—4.5 GB est.Yes
iMac (Apple M4)4bit—4.5 GB est.Yes
Mac mini (Apple M6)4bit—4.5 GB est.Yes
MacBook Air (Apple M5)4bit—4.5 GB est.Yes
MacBook Pro (Apple M5)4bit—4.5 GB est.Yes
Apple M24bit—4.5 GB est.Yes
Apple M34bit—4.5 GB est.Yes
Apple M14bit—4.5 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB4.5 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB4.5 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB4.5 GB est.Yes
NVIDIA A100 80GB4bit80 GB4.5 GB est.Yes
NVIDIA H100 SXM4bit80 GB4.5 GB est.Yes
NVIDIA H100 NVL4bit94 GB4.5 GB est.Yes
NVIDIA DGX Spark4bit128 GB4.5 GB est.Yes
NVIDIA H2004bit141 GB4.5 GB est.Yes
NVIDIA H200 NVL4bit141 GB4.5 GB est.Yes
NVIDIA B2004bit180 GB4.5 GB est.Yes
AMD Instinct MI300X4bit192 GB4.5 GB est.Yes
AMD Instinct MI325X4bit256 GB4.5 GB est.Yes
NVIDIA DGX B2004bit1,440 GB4.5 GB est.Yes
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, 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).

Timeline1

Full timeline →

Change history12

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
12 claims · 12 properties

Familyfamily1

Claim history for Family
ValueValid from → toStatusSourceConfidenceExtractor
Qwen → currentcurrentQwen — official blogT2mediumllm

Versionversion1

Claim history for Version
ValueValid from → toStatusSourceConfidenceExtractor
2.5 → currentcurrentQwen — official blogT2mediumllm

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
27 Mar 2025 → currentcurrentQwen — official blogT2mediumllm

Statusstatus1

Claim history for Status
ValueValid from → toStatusSourceConfidenceExtractor
active → currentcurrentQwen — official blogT2mediumllm

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentQwen — official blogT2mediumllm

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
Thinker-Talker (Transformer decoder with audio/image encoders, dual-track autoregressive Transformer Decoder for Talker) → currentcurrentQwen — official blogT2mediumllm

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
7B → currentcurrentQwen — official blogT2mediumllm

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
audio, image, speech, text, video → currentcurrentQwen — official blogT2mediumllm

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
audio, image, text, video → currentcurrentQwen — official blogT2mediumllm

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
speech, text → currentcurrentQwen — official blogT2mediumllm

Audioaudio1

Claim history for Audio
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentQwen — official blogT2mediumllm

Visionvision1

Claim history for Vision
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentQwen — official blogT2mediumllm

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

12

Source tiers

T212

Freshest observation

10 h ago

Conflicts

None

Source documents 1

Source documents
SourceDocumentTypeTierLast observedSnapshots
Qwen — official blogqwenlm.github.io/blog/qwen2.5-omni newsT1· Official10 h ago1

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

Data quality (53/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →