1. Models
  2. Qwen
  3. GPU memory usage comparison for Qwen2.5-Omni models
QwenX · Apr 30, 2025 · official

GPU memory usage comparison for Qwen2.5-Omni models

Qwen's bar chart drew 193.3K views on X: 0.7x its median post and #270 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Long context GPU memory decreases by 50%

XDataBar chartQwen OmniAll Qwen modelsQwen2.5-Omni 7BQwen2.5-Omni 3B
Published by Qwen on X, Apr 30, 2025. Source: x.com
84/ 100

ViralChart score

Reached and resonated

More views and a higher engagement rate than the median post: it travelled and people acted on it.

#15 of 1,162 AI chart posts we hold · #8 of 55 Qwen posts. Score = views 40%, likes 30%, engagement rate 15%, save rate 15%, each as a percentile of every AI chart post we hold.

Our read

The post sits in Reached and resonated, with a score rank of #15 of 1,162 AI chart posts.

Its score of 84 ranks #15 of 1,162 AI chart posts, above the median.

A 0.25% save rate sits at the 95th percentile among AI chart posts, 3.3x the 0.076% median.

The post carries 2 charts, and every chart in the post shares the post's numbers.

top 5%save rate

0.252% of viewers bookmarked it to come back to. The median post gets 0.076%.

2charts in this one post

The numbers belong to the post, so every chart in it shares them and it is ranked once.

top 13%engagement rate

1.29% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

2.2xthe median bar chart post

Across 108 bar chart posts we hold, the median gets 87.5K views.

Public X numbers from our read on Oct 13, 2026. Peers: 1,162 AI chart posts we hold and 55 from Qwen.

Where it sits

Reach against resonance

Each dot is a post. Right is more views, up is a higher engagement rate. The lines are the medians, so the four corners are the four kinds of post.

Among 1,162 AI chart posts we hold

Score #15 of 1,162

Views193.3K#270top 23%
Likes2.1K#143top 12%
Engagement rate1.29%#153top 13%
Save rate0.252%#64top 5%

Among 55 Qwen posts

Score #8 of 55

Views193.3K#31bottom 45%
Likes2.1K#22top 39%
Engagement rate1.29%#3top 5%
Save rate0.252%#7top 12%

Growth

Our reads cover 27 hours

Views193.3K
Age at our read531 days
Views per day of life364views divided by days since it was posted
Gained between our reads+1views over 27 hours, about 1 a day now

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

Qwen's posts over time

Every post from this account we hold, by date and views. This one is marked; the line is the running median of the last 10.

News · Apr 30, 2025

Qwen posts GPU memory comparison for Qwen2.5-Omni models

A bar chart on GPU memory usage for Qwen2.5-Omni models reached 193K views and a 0.25% save rate.

What happened

Qwen published a bar chart on GPU memory usage for Qwen2.5-Omni models on April 30, 2025. The post included 2 charts, the other being Qwen2.5-Omni Performance Comparison.

The numbers

The post drew 193K views, ranking #270 of 1,162 AI chart posts. Its score of 84 ranks #15 of 1,162 AI chart posts and #8 of 55 Qwen posts.

The lesson

A 0.25% save rate, 3.3x the AI chart median, shows that readers bookmark this GPU memory comparison. The 2 charts in the post share the post's numbers, so the save rate applies to both.

What it means

At #8 of 55 Qwen posts, this chart post sits in the account's top tier. The 3.3x gap to the AI chart median save rate marks it as a reference post for GPU memory comparisons.

Written by ViralChart from public numbers read on Oct 13, 2026. Every number is checked against our data before it is shown.

Updates: what Qwen posted next

  1. Qwen3-Coder Benchmarks2.3M views
  2. SWE-bench Verified Performance vs Model Size80.5K views
  3. Qwen3-Coder-Flash Benchmarks797.3K views
  4. AI Model Benchmark Comparison736.7K views
  5. ASR Error Rates - Public and Internal Tests265.9K views
  6. TTS Multilingual Performance Comparison122.2K views

Data and API

2 points read off this chart

Estimated from the image 97%
SeriesGroupValueRead
Qwen2.5-Omni 7B60.2printed
Qwen2.5-Omni 3B28.2printed

Max plan · API

GET https://viral-chart.com/api/posts/4dd56a36a879.json
GET https://viral-chart.com/api/charts/4dd56a36a879.json
GET https://viral-chart.com/api/charts/4dd56a36a879.skill.md
Make one like thisOpen the post JSONChart data JSONSkill fileAPI docs

Static files in this prototype. The post JSON holds the public numbers, ranks, score, quadrant, our reads and, when checked, our copy.

API · Max

Use this chart via API

On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id 4dd56a36a879.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/4dd56a36a879Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/4dd56a36a879/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/4dd56a36a879/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/4dd56a36a879/data \
  -H "Authorization: Bearer $VIRALCHART_KEY"
Claude CodeMax
claude mcp add --transport http viralchart https://viral-chart.com/mcp \
  --header "Authorization: Bearer $VIRALCHART_KEY"

60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.

More charts about Qwen Omni

Qwen Omni: Qwen3.5-Omni-Plus Benchmark Comparison
OfficialX · QwenMar 30, 2026
Qwen3.5-Omni-Plus Benchmark Comparison973.8K views · 4.5K likes
Data
Qwen Omni: Qwen2.5-Omni Performance Comparison
OfficialX · QwenApr 30, 2025
Qwen2.5-Omni Performance Comparison193.3K views · 2.1K likes
Data
Qwen Omni: Multimodal Model Performance Comparison
OfficialX · QwenMar 26, 2025
Multimodal Model Performance Comparison15.9K views · 141 likes
Data
Qwen Omni: Time to First Audio Generation
X · @ArtificialAnlysOct 8, 2025
Time to First Audio Generation82.2K views · 356 likes
Data
Qwen Omni: Artificial Analysis Intelligence Index v3.0
X · @ArtificialAnlysOct 8, 2025
Artificial Analysis Intelligence Index v3.06.3K views · 36 likes
Data

More from Qwen

Qwen grouped bar chart: AI model benchmark scores19x
Qwen·Jan 2025
AI model benchmark scores
3.1M views7.1K likes0.3% eng.
Data
Qwen small multiples: Agentic Environment Model Training13x
Qwen·Jun 2026
Agentic Environment Model Training
1.2M views4.9K likes0.5% eng.
Data
Qwen annotated chart: Qwen3-Omni architecture12x
Qwen·Sep 2025
Qwen3-Omni architecture
715.6K views4.3K likes0.8% eng.
Data
Qwen3: AI Model Benchmarks Comparison
OfficialX · QwenMar 2, 2026
AI Model Benchmarks Comparison9M views · 20.9K likes
Data
Qwen app and Qwen Chat: AI Model Benchmarks Comparison
OfficialX · QwenAug 3, 2026
AI Model Benchmarks Comparison7.3M views · 22.6K likes
Data
Qwen app and Qwen Chat: AI Model Benchmarks Comparison
OfficialX · QwenFeb 24, 2026
AI Model Benchmarks Comparison4M views · 7.9K likes
Data
Qwen app and Qwen Chat: AI Model Benchmarks Comparison
OfficialX · QwenApr 22, 2026
AI Model Benchmarks Comparison3.7M views · 12.3K likes
Data
Qwen app and Qwen Chat: AI Model Benchmarks Comparison
OfficialX · QwenMar 5, 2025
AI Model Benchmarks Comparison3.6M views · 8.6K likes
Data
Qwen app and Qwen Chat: AI Model Benchmarks Comparison
OfficialX · QwenApr 16, 2026
AI Model Benchmarks Comparison2.7M views · 11.3K likes
Data

Questions people ask

Where does this chart come from?

Qwen published it on Apr 30, 2025 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. Open its data page and use Make one like this: it starts from this chart's numbers and takes yours.