---
title: "Yobitel Communications (@yobitel) | Hashnode"
description: "Yobitel Communications (@yobitel) writes on Hashnode. Read their latest articles and follow their work."
url: "https://hashnode.com/@yobitel"
---

@yobitel

# Yobitel Communications

@yobitel · London, UK · Joined July 2026

### [How Do Growing Teams Structure a CVAT Annotation Workflow?](https://yobitel.hashnode.dev/how-do-growing-teams-structure-a-cvat-annotation-workflow?utm_source=hashnode&utm_medium=feed)

Structure CVAT annotation workflows with smart job sizing, task assignment, quality reviews and scalable AWS deployment using Yobitel's CVAT AMI.

10 min read · [yobitel.hashnode.dev](https://yobitel.hashnode.dev/how-do-growing-teams-structure-a-cvat-annotation-workflow?utm_source=hashnode&utm_medium=feed)

[2h ago](https://hashnode.com/posts/how-do-growing-teams-structure-a-cvat-annotation-workflow/6b012f667508ff968ecfb935)

### [How do you choose between g4dn, g5, and g6 instances for simulation?](https://yobitel.hashnode.dev/how-do-you-choose-between-g4dn-g5-and-g6-instances-for-simulation?utm_source=hashnode&utm_medium=feed)

Picking the wrong GPU instance crashes your GROMACS run or adds weeks to your deadline. Compare g4dn, g5, and g6 on memory, throughput, and power.

15 min read · [yobitel.hashnode.dev](https://yobitel.hashnode.dev/how-do-you-choose-between-g4dn-g5-and-g6-instances-for-simulation?utm_source=hashnode&utm_medium=feed)

[Oct 22](https://hashnode.com/posts/how-do-you-choose-between-g4dn-g5-and-g6-instances-for-simulation/6ad9d4708d1c721321c76777)

### [Inference endpoint - When to scale up or down?](https://yobitel.hashnode.dev/inference-endpoint-when-to-scale-up-or-down?utm_source=hashnode&utm_medium=feed)

Learn when to scale GPU inference endpoints up or down using queue depth, TTFT, and KV cache signals — plus A10G vs H100 cost math.

9 min read · [yobitel.hashnode.dev](https://yobitel.hashnode.dev/inference-endpoint-when-to-scale-up-or-down?utm_source=hashnode&utm_medium=feed)

[Oct 8](https://hashnode.com/posts/inference-endpoint-when-to-scale-up-or-down/6ac78712c38d0fcd467912f7)
