DEV Community

#benchmarking

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
My AI App Waits 2.3 Seconds Before Saying a Single Word. Here's Exactly Where That Time Goes.
vicarioy profile

My AI App Waits 2.3 Seconds Before Saying a Single Word. Here's Exactly Where That Time Goes.

#performance #llm #buildinpublic #benchmarking
1
Comments
6 min read
AI Agent Evaluation End to End: How LFORLA Scores a LEGO Build From Brief to Render
resk profile
RESK

AI Agent Evaluation End to End: How LFORLA Scores a LEGO Build From Brief to Render

#ai #benchmarking #agents #evaluation
Comments
5 min read
A Dense 31B on an 8 GB GPU: Gemma 4 31B on an RTX 3050
xbill profile

A Dense 31B on an 8 GB GPU: Gemma 4 31B on an RTX 3050

#gemma #llamacpp #cuda #benchmarking
8
Comments
10 min read
How Much Context Fits Beside a 12B on an 8 GB GPU? Gemma 4 12B's Context Cache on an RTX 3050
xbill profile

How Much Context Fits Beside a 12B on an 8 GB GPU? Gemma 4 12B's Context Cache on an RTX 3050

#gemma #llamacpp #cuda #benchmarking
2
Comments
9 min read
Benchmarking an Agent Without Lying to Yourself
harrisonsec profile

Benchmarking an Agent Without Lying to Yourself

#ai #machinelearning #benchmarking #testing
Comments
5 min read
Benchmarking S3 Throughput: How to Measure Without Lying
ethan-carter profile

Benchmarking S3 Throughput: How to Measure Without Lying

#s3 #performance #benchmarking #storage
Comments
11 min read
csperf Diff: Comparing Two Runs Without Spreadsheet Chaos
aabhinavg profile

csperf Diff: Comparing Two Runs Without Spreadsheet Chaos

#csperf #diff #benchmarking #performance
Comments
4 min read
Can a 26B MoE Run on an 8 GB GPU? Gemma 4 26B A4B on an RTX 3050
xbill profile

Can a 26B MoE Run on an 8 GB GPU? Gemma 4 26B A4B on an RTX 3050

#gemma #llamacpp #cuda #benchmarking
10
Comments 2
11 min read
We Wanted a Fast Offline AI. First, We Had to Fix Our Benchmark.
lastbrowser profile

We Wanted a Fast Offline AI. First, We Had to Fix Our Benchmark.

#webdev #ai #llm #benchmarking
Comments
22 min read
I Built a Benchmark That Catches AI Models Cheating (And They All Failed)
ratnesh_saxena profile

I Built a Benchmark That Catches AI Models Cheating (And They All Failed)

#kagglechallenge #ai #llm #benchmarking
Comments
3 min read
Noise Sources: Affinity, Frequency, and Background Load — How to isolate and quantify non‑compiler variance with csperf
aabhinavg profile

Noise Sources: Affinity, Frequency, and Background Load — How to isolate and quantify non‑compiler variance with csperf

#methodology #benchmarking #csperf #performance
Comments
3 min read
Kev gives the same answer every time. Until you batch it.
guichard profile

Kev gives the same answer every time. Until you batch it.

#ai #machinelearning #opensource #benchmarking
Comments
8 min read
Do Drafters Work on Small Models? Gemma 4 E2B and E4B on Two Small GPUs

Acceptance rates hold steady across hardware
xbill profile

Do Drafters Work on Small Models? Gemma 4 E2B and E4B on Two Small GPUs

#gemma #llamacpp #cuda #benchmarking
8
Comments 3
19 min read
I Tested Whether Frontier AI Can Do a Texas Real Estate Agent's Desk Work — Here's What 3 Models Taught Me (and What the 4th Taught Me About Benchmarks)

Kaggle Benchmarking Challenge Submission
brandon_favor_cf98fad9596 profile

I Tested Whether Frontier AI Can Do a Texas Real Estate Agent's Desk Work — Here's What 3 Models Taught Me (and What the 4th Taught Me About Benchmarks)

#kagglechallenge #ai #llm #benchmarking
Comments
6 min read
Can a QAT 12B Fit an 8 GB GPU? Gemma 4 12B on an RTX 3050
xbill profile

Can a QAT 12B Fit an 8 GB GPU? Gemma 4 12B on an RTX 3050

#gemma #llamacpp #cuda #benchmarking
7
Comments
15 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.