DEV Community

#gpu

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
DeepSeek V4.1 Flash at 42 tok/s with 256K Context on RTX 5070 Ti x2 + 5060 Ti — Full Benchmark Record

DeepSeek V4.1 Flash at 42 tok/s with 256K Context on RTX 5070 Ti x2 + 5060 Ti — Full Benchmark Record

Comments
10 min read
How much GPU memory does an LLM need? The whole sum, worked out on real cards

How much GPU memory does an LLM need? The whole sum, worked out on real cards

Comments
9 min read
Local AI on a PC: what actually works (Whisper, translation, LLMs)

Local AI on a PC: what actually works (Whisper, translation, LLMs)

Comments
2 min read
When does reserved GPU capacity beat on-demand pricing?

When does reserved GPU capacity beat on-demand pricing?

Comments
9 min read
How many tokens per second should an LLM serve on one GPU?

How many tokens per second should an LLM serve on one GPU?

Comments
8 min read
What are the best Shadeform alternatives for buying GPU time?

What are the best Shadeform alternatives for buying GPU time?

Comments
9 min read
Why can a multi-GPU job wait while GPUs are idle?

Why can a multi-GPU job wait while GPUs are idle?

Comments
4 min read
How Much VRAM Does Your LLM Need? The Math Behind the EverXCloud Calculator

How Much VRAM Does Your LLM Need? The Math Behind the EverXCloud Calculator

Comments
4 min read
How many LLM agent sessions can one GPU serve? Measured: 8 to 256 sessions on one NVIDIA L4, every step exact

How many LLM agent sessions can one GPU serve? Measured: 8 to 256 sessions on one NVIDIA L4, every step exact

Comments
4 min read
Custo de GPU na RunPod em reais: a conta por hora ligada

Custo de GPU na RunPod em reais: a conta por hora ligada

Comments
2 min read
A slow GPU isn't a broken GPU: grading GPUs per workload in Kubernetes (measured on real A10Gs)

A slow GPU isn't a broken GPU: grading GPUs per workload in Kubernetes (measured on real A10Gs)

Comments
5 min read
PyTorch Passed Silently. The Job Would Have Failed 20 Minutes In.

PyTorch Passed Silently. The Job Would Have Failed 20 Minutes In.

Comments
2 min read
What is a serverless GPU, and when should you use one?

What is a serverless GPU, and when should you use one?

Comments
8 min read
LLM selbst hosten oder per Token abrechnen? Ein Rechenweg fĂĽr Teams in der EU

LLM selbst hosten oder per Token abrechnen? Ein Rechenweg fĂĽr Teams in der EU

Comments
5 min read
How to Estimate Your FPS Before You Buy a Game or Upgrade Your GPU

How to Estimate Your FPS Before You Buy a Game or Upgrade Your GPU

Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.