Models
Meta
Output Tokens per Second: Llama 4 Maverick Providers

@ArtificialAnlysX · May 29, 2025

Output Tokens per Second: Llama 4 Maverick Providers

@ArtificialAnlys's bar chart drew 20.4K views on X: 1.8x @artificialanlys's median post and #716 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

XData Bar chart Llama 4 All Meta modelsCerebras (private endpoint)NVIDIA (private endpoint)SambaNovaGroqAmazonLambda Labs (FP8)Google VertexTogether.ai (FP8)

@ArtificialAnlys: Output Tokens per Second: Llama 4 Maverick Providers — Published by @ArtificialAnlys on X, May 29, 2025. Source: x.com

53/ 100

ViralChart score

Small but loved

Fewer views than the median post but a higher engagement rate: a smaller crowd that acted on it.

#585 of 1,162 AI chart posts we hold · #181 of 491 @artificialanlys 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

It sits in the Small but loved quadrant, at #585 of 1,162 AI chart posts.

Its 1.22% engagement rate sits at the 84th percentile among AI chart posts, against a 0.73% median.

The account posted 3 times that day, and this post ranked #2 of 3 by views.

At 20.4K views it runs 1.8x the company median of 11.4K.

top 16%engagement rate

1.22% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

3posts from @artificialanlys that day

Part of a run of 3 posts on May 29, 2025. This one was #2 of 3 by views that day.

top 28%save rate

0.122% of viewers bookmarked it to come back to. The median post gets 0.076%.

1.8x@artificialanlys's median post

20.4K views, where @artificialanlys's typical post gets 11.4K.

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 491 from @artificialanlys.

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 #585 of 1,162

Views	20.4K	#716	bottom 38%
Likes	219	#629	bottom 46%
Engagement rate	1.22%	#185	top 16%
Save rate	0.122%	#323	top 28%

Among 491 @artificialanlys posts

Score #181 of 491

Views	20.4K	#212	top 43%
Likes	219	#184	top 37%
Engagement rate	1.22%	#95	top 19%
Save rate	0.122%	#156	top 32%

Growth

One read so far

Views20.4K

Age at our read502 days

Views per day of life41views divided by days since it was posted

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

@artificialanlys'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 · May 29, 2025

@ArtificialAnlys charts Llama 4 Maverick output tokens per second

A bar chart of output tokens per second across Llama 4 Maverick providers drew 20.4K views and a 1.22% engagement rate.

What happened

@ArtificialAnlys posted a bar chart on May 29, 2025, on output tokens per second for Llama 4 Maverick providers. That day the account posted 3 times, including an Artificial Analysis Intelligence Index post at 630K views.

The numbers

It reached 20.4K views, #716 of 1,162 AI chart posts, and scored #585 of 1,162 AI chart posts. Among @ArtificialAnlys posts it ranks #181 of 491 by score and #212 of 491 by views.

The lesson

A 1.22% engagement rate at the 84th percentile came with a 0.12% save rate. The chart shows printed values from 2522 down to 160, and readers engaged without saving it at the same rate.

What it means

At 20.4K views against a 39.9K median among AI chart posts, this post ran below the median reach while its 1.22% engagement rate cleared the 0.73% median. For @ArtificialAnlys, the gap is reach, not engagement.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what @artificialanlys posted next

Data and API

9 points read off this chart

Estimated from the image 97%

Group	Value	Read
Cerebras (private endpoint)	2522 tokens/s	printed
NVIDIA (private endpoint)	1038 tokens/s	printed
SambaNova	794 tokens/s	printed
Groq	549 tokens/s	printed
Amazon	290 tokens/s	printed
Lambda Labs (FP8)	160 tokens/s	printed
Google Vertex	125 tokens/s	printed
Together.ai (FP8)	120 tokens/s	printed
Azure (FP8)	54 tokens/s	printed

Max plan · API

GET https://viral-chart.com/api/posts/9c3d804a320a.json
GET https://viral-chart.com/api/charts/9c3d804a320a.json
GET https://viral-chart.com/api/charts/9c3d804a320a.skill.md

Make one like this Open the post JSON Chart data JSON Skill file API 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 9c3d804a320a.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/9c3d804a320a`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/9c3d804a320a/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/9c3d804a320a/render?view=1`	The draw-only view this page uses	Open
POST	`/mcp`	Tool get_chart_data with this id, for Claude, Cursor and other agents	Max

curlMax

curl -s https://viral-chart.com/api/v1/charts/9c3d804a320a/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.