DEV Community

Maxim Saplin profile picture

Maxim Saplin

ツ Manager, Engineer, Open-source Maintainer

Education

Computer Science @BNTU, MBA @BSU

Work

EPAM, Delivery Partner

Writing Debut
16 Week Writing Streak
Four Year Club
8 Week Writing Streak
4 Week Community Wellness Streak
2 Week Community Wellness Streak
4 Week Writing Streak
1 Week Community Wellness Streak
Three Year Club
Two Year Club
One Year Club
DDR5 Speed, CPU and LLM Inference

DDR5 Speed, CPU and LLM Inference

8
Comments
4 min read

Want to connect with Maxim Saplin?

Create an account to connect with Maxim Saplin. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
Gen AI Hype - the Never Ending Excitement

Gen AI Hype - the Never Ending Excitement

11
Comments
8 min read
OpenAI o1 Release is so Reminiscent of Apple Events - it's an Incremental Update

OpenAI o1 Release is so Reminiscent of Apple Events - it's an Incremental Update

14
Comments 4
7 min read
Continue.dev: The Swiss Army Knife That Sometimes Fails to Cut

Continue.dev: The Swiss Army Knife That Sometimes Fails to Cut

14
Comments
8 min read
Python 3.13 RC1 - a Quick CPU Benchmark

Python 3.13 RC1 - a Quick CPU Benchmark

9
Comments 1
2 min read
llama.cpp: CPU vs GPU, shared VRAM and Inference Speed

llama.cpp: CPU vs GPU, shared VRAM and Inference Speed

16
Comments 5
3 min read
Convergence of LLMs: 2024 Trend Solidified by Llama 3.1 Release

Convergence of LLMs: 2024 Trend Solidified by Llama 3.1 Release

12
Comments 4
3 min read
DoLa and MT-Bench - A Quick Eval of a new LLM trick

DoLa and MT-Bench - A Quick Eval of a new LLM trick

6
Comments
2 min read
4090 - ECC ON vs ECC OFF

4090 - ECC ON vs ECC OFF

7
Comments
1 min read
MT-Bench: Comparing different LLM Judges

MT-Bench: Comparing different LLM Judges

11
Comments 1
4 min read
Nvidia's 1000x Performance Boost Claim Verified

Nvidia's 1000x Performance Boost Claim Verified

12
Comments
2 min read
LLM Fine-tunig on RTX 4090: 90% Performance at 55% Power

LLM Fine-tunig on RTX 4090: 90% Performance at 55% Power

20
Comments
2 min read
GPT-4o: sneak peak at Llama 3 400B and the Age of Loneliness...

GPT-4o: sneak peak at Llama 3 400B and the Age of Loneliness...

24
Comments 1
3 min read
FineWeb 45TB Dataset: $500k GPU costs and Adult Content Improving LLM Quality

FineWeb 45TB Dataset: $500k GPU costs and Adult Content Improving LLM Quality

12
Comments 1
2 min read
Llama 3 8B is better than Llama 2 70B

Llama 3 8B is better than Llama 2 70B

20
Comments
1 min read
Fine-tuning LLM on a laptop: VRAM - Shared Memory - GPU Load - Performance

Fine-tuning LLM on a laptop: VRAM - Shared Memory - GPU Load - Performance

9
Comments
3 min read
3 Manifestations of GenAI in Software Development

3 Manifestations of GenAI in Software Development

6
Comments
1 min read
AI-assisted coding, Sleeping on a Volcano

AI-assisted coding, Sleeping on a Volcano

15
Comments 1
9 min read
LLM's "commendable, innovative, meticulous, notable, versatile, intricate" impact

LLM's "commendable, innovative, meticulous, notable, versatile, intricate" impact

14
Comments
2 min read
Running Local LLMs, CPU vs. GPU - a Quick Speed Test

Running Local LLMs, CPU vs. GPU - a Quick Speed Test

163
Comments 36
4 min read
Apple is killing PWA?

Apple is killing PWA?

42
Comments 15
8 min read
Memories in ChatGPT: Privacy Implications

Memories in ChatGPT: Privacy Implications

8
Comments
3 min read
Apple Vision Pro is the best marketing campaign for Meta's Quest 3

Apple Vision Pro is the best marketing campaign for Meta's Quest 3

12
Comments 4
2 min read
⟨ Cursor.sh ⟩ - a competitor to GitHub CoPilot

⟨ Cursor.sh ⟩ - a competitor to GitHub CoPilot

94
Comments
10 min read
Google's Slow Burn: Project IDX's Half-Year Echo

Google's Slow Burn: Project IDX's Half-Year Echo

11
Comments
2 min read
C#, Dart, TypeScript , Python: side-by-side

C#, Dart, TypeScript , Python: side-by-side

28
Comments 10
7 min read
Chatting with AI: The Freedom of Private Interfaces

Chatting with AI: The Freedom of Private Interfaces

13
Comments 2
8 min read
Phi-2 is available for chat through LM Studio Beta

Phi-2 is available for chat through LM Studio Beta

10
Comments
2 min read
How fast is JS tiktoken?

How fast is JS tiktoken?

10
Comments
1 min read
`Get Abstract` for Lex Fridman and Jeff Bezos talk (December 2023)

`Get Abstract` for Lex Fridman and Jeff Bezos talk (December 2023)

8
Comments
3 min read
Python 3.12 Performance - a Quick Test

Python 3.12 Performance - a Quick Test

33
Comments 6
2 min read
Google's Future: A Tale of Two Ex-Googlers

Google's Future: A Tale of Two Ex-Googlers

26
Comments
4 min read
Claude 2.1 AI model with 200K Context is Live

Claude 2.1 AI model with 200K Context is Live

10
Comments 3
2 min read
GPT-4, 128K context - it is not big enough

GPT-4, 128K context - it is not big enough

39
Comments 4
7 min read
All {M3 MacBook Pro} configs: Ranking by Compute/RAM/SSD per $

All {M3 MacBook Pro} configs: Ranking by Compute/RAM/SSD per $

7
Comments
2 min read
What's new in OpenAI - Announcements at Nov'2023 DevDay

What's new in OpenAI - Announcements at Nov'2023 DevDay

16
Comments
2 min read
The Art of Simplicity | Apple ID vs Google Account

The Art of Simplicity | Apple ID vs Google Account

9
Comments
1 min read
Embrace Functional Programming with /Dart 3.1/

Embrace Functional Programming with /Dart 3.1/

18
Comments 2
6 min read
Android's `monospace` font is not monospace

Android's `monospace` font is not monospace

4
Comments
1 min read
AI coding assistant | API Costs

AI coding assistant | API Costs

10
Comments
2 min read
C# `float` vs `double`: Performance Considerations

C# `float` vs `double`: Performance Considerations

14
Comments 1
2 min read
DEV: Followers != Readers

DEV: Followers != Readers

34
Comments 23
1 min read
Mojo🔥: Head-to-Head with Python and Numba

Mojo🔥: Head-to-Head with Python and Numba

20
Comments 1
4 min read
Integrating Flutter {all 6 platforms} and Python: Part 2, Live Talk

Integrating Flutter {all 6 platforms} and Python: Part 2, Live Talk

8
Comments 1
1 min read
Flet is "The fastest way to build Flutter apps in Python" - it's not :(

Flet is "The fastest way to build Flutter apps in Python" - it's not :(

37
Comments 4
3 min read
Mojo🔥SDK has been released for Linux

Mojo🔥SDK has been released for Linux

9
Comments 8
1 min read
AI coding tools are good at simple tasks. McKinsey and GitHub data suggests

AI coding tools are good at simple tasks. McKinsey and GitHub data suggests

14
Comments
2 min read
fartlang.org

fartlang.org

9
Comments 3
1 min read
OpenAI `function calling` to enforce reply format/schema

OpenAI `function calling` to enforce reply format/schema

11
Comments
3 min read
"Smart" Refactoring with AI 〉beyond Old School Refactors

"Smart" Refactoring with AI 〉beyond Old School Refactors

6
Comments
2 min read
Project IDX by Google 〉Web, Flutter, AI... It's not there yet 💩

Project IDX by Google 〉Web, Flutter, AI... It's not there yet 💩

6
Comments
2 min read
Exploring Cody - An AI Coding Assistant That Knows Your Codebase

Exploring Cody - An AI Coding Assistant That Knows Your Codebase

10
Comments 6
6 min read
loading...