Benchmark - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Oct 18

ComfyUI vs Forge on a 16 GB GPU: a tie on SDXL, ComfyUI twice as fast when the model does not fit

#stablediffusion #ai #gpu #benchmark

2 min read

Oct 18

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

#llm #gpu #vllm #benchmark

2 min read

Jin

Oct 18

Best AI Coding Agent for the Money: What Databricks’ Benchmark Reveals

#ai #agents #databricks #benchmark

2 min read

Vikas Srivastava

Oct 18

Your Agent Benchmark Pauses the World. Production Doesn't.

#transformers #agents #benchmark #testing

4 min read

RESK

Oct 18

How an LLM Evaluation Benchmark Produces Comparable Numbers: Inside the LFORLA Mechanism

#llm #evaluation #benchmark #ai

4 min read

Semurg

Oct 18

Graph on one server: a 4-hop query 19 to 388 times faster than the incumbents

#graph #database #benchmark #performance

4 min read

Oct 18

Our agentic coding benchmark results are now an open dataset on Hugging Face

#ai #llm #benchmark #huggingface

3 min read

Oct 18

NVFP4 vs FP8 vs GGUF on a 16 GB Ada GPU: NVFP4 decodes 2.3x faster and ties BF16 on GSM8K

#llm #machinelearning #gpu #benchmark

2 min read

EME GUG

Oct 17

Your GPU Benchmark Is Lying: Measuring LLM Inference Under Thermal Throttling the Right Way

#llm #gpu #benchmark #performance

7 min read

LeoJulieta

Oct 17

Llmspeed Benchmark: Pick the Perfect On‑Device LLM Hardware Fast

#llmspeed #benchmark #hardware #english

4 min read

LeoJulieta

Oct 17

Llmspeed: Benchmark rápido de LLMs com latência, throughput e TCO

#llmspeed #benchmark #hardware #portugues

3 min read

LeoJulieta

Oct 17

Llmspeed: Mide el rendimiento de LLMs locales en minutos

#llmspeed #benchmark #hardware #espanol

4 min read

RESK

Oct 16

AI Bias Detection: How a Fairness Audit Actually Works

#ai #fairness #benchmark #llm

3 min read

Oct 15

Your agent benchmark's "user" is a second model, and 24.4% of its successful runs broke the user's own script

#ai #testing #llm #benchmark

7 min read

Oct 14

Kandinsky 6.0 on a 16 GB GPU: the official recipe runs out of memory, and only the 29B model passed my Spanish test

#ai #machinelearning #gpu #benchmark

2 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.