the amd instinct mi300x gpu can handle the meta llama 60b parameter model on a single gpu. #amd
Published 1 year ago • 27K plays • Length 0:25Download video MP4
Download video MP3
Similar videos
-
1:00
jordan getting hands-on with the amd instinct mi300 gpus, walking through key features. 2 of 2.
-
7:25
amd reveals mi300x ai chip (watch it here)
-
1:39
introducing amd instinct™ mi300 series accelerators
-
5:32
new gpu for ai inference & fine-tuning llms - mi300x
-
51:15
webinar - getting started with llama3 on amd radeon and instinct gpus
-
5:15
llama 3.1 70b gpu requirements (fp32, fp16, int8 and int4)
-
5:48
ollama llama3-8b speed compairson with different nvidia gpu and fp16/q8_0 quantification
-
6:27
6 best consumer gpus for local llms and ai software in late 2024
-
17:40
deep-dive into the technology of amd's mi300
-
8:18
llama 3.2 is beating openai at their own game (real-time ai voice, vision...)
-
10:23
build dual gpus system for ai: dual 3060ti run llama (exllama)
-
1:22
introducing the amd instinct™ mi200 series accelerator
-
4:50
amd gpu 6700xt run llama 3.1 (ollama run llama3.1)
-
19:38
amd takes ai-m at nvidia with mi300x, mi300a and mi300c
-
6:32
nvidia llama 3.1 minitron 4b: create ai with 1.8x cost savings
-
16:24
amd's $25,000 gpu: instinct mi210 tear-down ft. level1techs
-
0:23
llamafile cpu vs gpu
-
12:24
run llama 3 on linux | build with meta llama
-
3:42
[meta llama] download explosion: 350 million and counting!
-
16:13
nvidia rtx 3000! new cooler, ampere architecture, performance & more...
-
5:44
ai llama3.1 70b on 32gb ram - fail but close...
-
14:47
rtx 3000s - is nvidia crushing amd for good?