PulseAugur
EN
LIVE 14:40:23

RTX 3090 vs L40S: Batch size dictates GPU performance and cost

By PulseAugur Editorial · [1 sources] ·

A performance comparison between the RTX 3090 and L40S GPUs reveals that the 3090 is faster at batch size 1, outperforming the L40S by up to 1.11x. However, the L40S significantly pulls ahead at larger batch sizes, reaching up to 0.46x the speed of the 3090 at batch size 128. Cost-effectiveness also varies by batch size, with the 3090 being cheaper for small batches and the L40S becoming more economical for larger, more consistent workloads. AI

IMPACT Performance and cost differences highlight the importance of matching hardware to specific LLM workload batch sizes for optimal efficiency.

RANK_REASON Benchmarking study comparing hardware performance for LLM inference. [lever_c_demoted from research: ic=1 ai=0.7]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

RTX 3090 vs L40S: Batch size dictates GPU performance and cost

How we ranked this

Signal score
25 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Benchmarking study comparing hardware performance for LLM inference. [lever_c_demoted from research: ic=1 ai=0.7]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Qaiser Mehdi ·

    A 3090 vs an L40S: 1.09x at batch 1, 0.46x at batch 128

    <p>People ask "is a 3090 as fast as an L40S?" and want one number. I measured both on my own rented machines, same script, and there is no one number. It depends on how many requests you run at once.<br /> Setup: vLLM 0.27.1, Qwen2.5 1.5B and 7B (plain and AWQ), 128 output tokens…

RELATED ENTITIES

RELATED TOPICS