Models
Qwen
Peak Inference Memory at 4K Context

@ArtificialAnlysX · Aug 24, 2026

Peak Inference Memory at 4K Context

@ArtificialAnlys's bar chart drew 4.3K views on X: 0.4x @artificialanlys's median post and #979 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Peak memory usage at 4K context

XData Bar chart Qwen3 All Qwen modelsLlama 3.2-3BLlama 3.2-1BGranite 4.0-3BMinistral-3BLlama 3.1-8BLlama 2-7BLlama 2-13BGemma 2-9B

@ArtificialAnlys: Peak Inference Memory at 4K Context — Published by @ArtificialAnlys on X, Aug 24, 2026. Source: x.com

26/ 100

ViralChart score

Small but loved

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

#985 of 1,162 AI chart posts we hold · #358 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 #985 of 1,162 AI chart posts.

Its score of 26 sits at #985 of 1,162 AI chart posts, below the field.

At 4.3K views against a company median of 11.4K, the post runs 0.38x the @ArtificialAnlys norm.

Saves land at 0.047%, the 26th percentile among AI chart posts and below the 0.076% median.

0.2xthe median bar chart post

Across 241 bar chart posts we hold, the median gets 25.6K views.

4posts from @artificialanlys that day

Part of a run of 4 posts on Aug 24, 2026. This one was #2 of 4 by views that day.

0.4x@artificialanlys's median post

4.3K views, where @artificialanlys's typical post gets 11.4K.

bottom 26%save rate

0.047% of viewers bookmarked it to come back to. The median post gets 0.076%.

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 #985 of 1,162

Views	4.3K	#979	bottom 16%
Likes	34	#940	bottom 19%
Engagement rate	0.91%	#388	top 33%
Save rate	0.047%	#860	bottom 26%

Among 491 @artificialanlys posts

Score #358 of 491

Views	4.3K	#356	bottom 28%
Likes	34	#335	bottom 32%
Engagement rate	0.91%	#198	top 40%
Save rate	0.047%	#349	bottom 29%

Growth

One read so far

Views4.3K

Age at our read49 days

Views per day of life87views 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 · Aug 24, 2026

@ArtificialAnlys charts peak inference memory at 4K context

A bar chart of peak memory at 4K context drew 4.3K views and a 0.91% engagement rate, with saves below the AI chart median.

What happened

@ArtificialAnlys posted a bar chart on peak inference memory at 4K context on August 24, 2026. It was one of 4 posts from the account that day, alongside Mobile Device Benchmark Evaluations, Average Score vs Output Tokens and AI model performance.

The numbers

The post reached 4.3K views, #979 of 1,162 AI chart posts, and #356 of 491 @ArtificialAnlys posts. Its score of 26 ranks #985 of 1,162 AI chart posts and #358 of 491 @ArtificialAnlys posts.

The lesson

A 19-model bar chart saved at 0.047%, the 26th percentile among AI chart posts, against a 0.076% median. The chart shows peak memory values from 0.4 to 1.9, and the save rate sits below the field.

What it means

At 0.38x the @ArtificialAnlys median of 11.4K views, this post lands at #358 of 491 of the account's posts. The gap to the 39.9K median among AI chart posts is 4.3K against 39.9K.

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

32 points read off this chart

Estimated from the image 62%

Group	Value	Read
LFM2.5-230M	0.4 GB	printed
LFM2.5-350M	0.4 GB	printed
Granite 4.0.35B (Reasoning)	0.6 GB	printed
MiniCPM3-8B (Reasoning)	1 GB	printed
LFM2.5-1.2B-Instruct	1.1 GB	printed
LFM2.5-2.5B-Exp	1.9 GB	printed
LFM2.5-2.5B	2.3 GB	printed
Grok-3.5B	2.5 GB	printed
Gemma 4 E2B (Reasoning)	3.8 GB	printed
Nanobanana-2-8B	4 GB	printed
Qwen3.5-4B (Reasoning)	4.2 GB	printed
Falcon-H1-7B	5.2 GB	printed

Showing 12 of 32. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/b17556cd7448.json
GET https://viral-chart.com/api/charts/74582815e9ae.json
GET https://viral-chart.com/api/charts/74582815e9ae.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 74582815e9ae.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/74582815e9ae`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/74582815e9ae/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/74582815e9ae/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/74582815e9ae/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.