anubhav200
Joined 7 years ago
Karma
15
Submissions
22
Member since
Aug 4
Recent submissions
Comment · 4 months ago
I have been using qwen and glm based models from last 2 years, ended up buying mutiple machines for the same. Overall i feel 24vram is a must have to get get performance (speed wise) to match hosted soln. I have 2 machines a 12gb vram one and a 24gb one. On 12gb vram i get around 50tps generation and 500tps prompt processing and on 24gb one i get 180tps generation and 3500tps prompt processing. I have different configs for different scenarios and I also use llama cpp manager manage all my configs (https://github.com/anubhavgupta/llama-cpp-manager)
Comment · 4 months ago
Yes, llama.cpp, qwen 27b and 35b, llama-cpp-manager for managing model configs.(https://github.com/anubhavgupta/llama-cpp-manager)
Comment · 4 months ago
Yes, llama.cpp, qwen27b, 35b, claude code. Llama-cpp-manager for managing llama.cpp configs (https://github.com/anubhavgupta/llama-cpp-manager)
Comment · 6 months ago
All whisper models listed here: https://huggingface.co/anubhav200
Comment · 6 months ago
Yes
Comment · 1 year ago
Great work
Comment · 3 years ago
title is incorrect.
Comment · 3 years ago
WOW
Comment · 4 years ago
Thanks, I was looking for exactly this only.
Comment · 4 years ago
Is the syntax of shader programming language finalized ?
Comment · 4 years ago
Download link?
Comment · 5 years ago
I created React Native styling library that support media queries and it even lets you create your own style rule.