Mistral 7B LLM AI Leaderboard: The King of the Leaderboard? Nvidia RTX 3090 Vision 24GB throw down!

preview_player
Показать описание
Mistral 7B LLM AI Leaderboard: The King of the Leaderboard? Nvidia RTX 3090 Vision 24GB throw down!

This week in the RoboTF lab:
We put the current king in the lab through the Mistral 7B Leaderboard tests as the 3090 said it wanted to de-throne the 4070Ti Super from the last video in the series. Can the 3090 do it? Will it suck enough power to cook a pizza?

Final results at 11 Min Mark.

Just a fun time in the lab, grab your favorite relaxation method and join in.

GPU Bench Node (These are affiliate-based links that help the channel if you purchase from them!)

Recorded and best viewed in 4K
Your results may vary due to hardware, software, model used, context size, weather, wallet, and more!
  1. RoboTF AI
  2. Mistral 7B
  3. AI Leaderboard
  4. Nvidia RTX 3090
  5. GPU benchmarking
  6. LLM testing
Рекомендации по теме
Mistral 7B LLM 0:20:31

Mistral 7B LLM AI Leaderboard: Apple M1 Max MacBook Pro uses Metal to take on GPU's for their s...

Mistral 7B LLM 0:16:30

Mistral 7B LLM AI Leaderboard: i5-12450H 32GB DDR4 Mini PC takes on the leaderboard?

Mistral 7B LLM 0:15:36

Mistral 7B LLM AI Leaderboard: The King of the Leaderboard? Nvidia RTX 3090 Vision 24GB throw down!

Mistral 7B LLM 0:21:15

Mistral 7B LLM AI Leaderboard: Nvidia RTX A4500 GPU 20GB Where does prosumer/enterprise land?

Mistral 7B LLM 0:26:49

Mistral 7B LLM AI Leaderboard: GPU Contender Nvidia Tesla M40 24GB

Mistral 7B LLM 0:16:46

Mistral 7B LLM AI Leaderboard: GPU Contender Nvidia RTX 4060Ti 16GB

Mistral 7B LLM 0:19:27

Mistral 7B LLM AI Leaderboard: Unboxing an Nvidia RTX 4070Ti Super 16GB and giving it run!

Mistral 7B LLM 0:12:09

Mistral 7B LLM AI Leaderboard: Baseline Testing Q3 CPU Inference i9-9820X

Mistral 7B LLM 0:34:32

Mistral 7B LLM AI Leaderboard: Rules of Engagement and first GPU contender Nvidia Quadro P2000

Mistral 7B LLM 0:36:12

Mistral 7B LLM AI Leaderboard: Baseline Testing Q3,Q4,Q5,Q6,Q8, and FP16 CPU Inference i9-9820X

Mistral 7B LLM 0:17:00

Mistral 7B LLM AI Leaderboard: Unboxing an Nvidia RTX 4090 Windforce 24GB Can it break 100 TPS?

Mistral 7B LLM 0:29:10

Mistral 7B LLM AI Leaderboard: Unboxing AsRock Intel ARC A770 16GB and running it through our tests!

Mistral 7B LLM 0:25:55

Mistral 7B LLM AI Leaderboard: GPU Contender Nvidia GTX 1660

4070Ti Super 16GB 0:00:38

4070Ti Super 16GB vs Mistral 7B 0.3 FP16 AI/LLM Leaderboard

How To Run 0:10:30

How To Run Mistral 8x7B LLM AI RIGHT NOW! (nVidia and Apple M1)

Mistral 7B 🖖 0:13:11

Mistral 7B 🖖 Beats LLaMA2 13b AND Can Run On Your Phone??

Mistral, LLaMa & 0:38:59

Mistral, LLaMa & Co. - Kostenlose KI-Giganten lokal nutzen

Experiment26-7B: Brute Forcing 0:11:33

Experiment26-7B: Brute Forcing 1st Place on the Open LLM Leaderboard!

Best coding LLM? 0:09:48

Best coding LLM? (sonnet 3.5? llama 3.1? Deepseek-coder v2? gpt4o?)

Intel’s Neural Chat 0:06:51

Intel’s Neural Chat is Top-Ranked 7B Chat Model on the Leaderboard | Train models on CPUs

How they All 0:20:30

How they All Cheated the Ai Leaderboard

Top 7B AI 0:01:00

Top 7B AI Model and How it was Trained (Mistral + DPO) by Cultrix

Why Mistral AI 0:07:16

Why Mistral AI LLMs will overtake ChatGPT

NEW Mixtral 8x22b 0:12:03

NEW Mixtral 8x22b Tested - Mistral's New Flagship MoE Open-Source Model

Комментарии
Автор

If you get the chance could you run tests on intel a770 and 7900xtx . I want to know how far behind are them compared to nvidia.

iniyan
Автор

you can undervolt the 3090 and will use around 280 watts with basically the same speed :) (only like 3% slower)
(And if you use tensor cores, the core can run at 1500mhz while the tensors run the same speed and around 280 watts total)

ArtificialLife-GameOfficialAcc
Автор

Excellent video. I've been thinking about getting a AMD 7900XTX since it has 24GB but it is less than $900 new since ROC supports interface on LM Studio. I checked out the website and didn't find any AMD GPU testing. Any thoughts?

shawnvines
Автор

Mistral is the only AI I like and trust. These AI's eat a lot of power, yet they expect us to go green ??? What do you mean by fully offloaded ?

Matlockization