Local AI Speed Test: Qwen3, Llama, GPT-OSS and Deepseek model tested

Today, I'm gonna compare the speeds of different local LLMs models.
I'm using Ollama with OpenWebUI as interface on my X99 server.
ATTENTION: Nothing the LLMs said in the video was checked, it's just a speed comparison, accuracy wasn't counted.
The specs for my server are:
CPU: Intel Xeon E5 2680 V4
RAM: 32 GB DDR4 2133 MHz
GPU: Nvidia Tesla P100 PCIE (16 GB HBM2) Power limited at 125W for cooling purposes (10-20% performance loss in those tests)
Motherboard: chinese x99 from Aliexpress (Mougol X99 bundle CPU + RAM)
Storage: 4x 1 TB HDDs, 1 256 GB SATA Samsung SSD, 1 NvMe PCIE 3.0 4x Patriot 512 GB.
Timestamps:

0:00 GPT OSS
2:20 Llama3.1 8b Q8
4:00 Llama2 Uncensored 7b Q4
5:00 Llama3.2 3b Q5
6:00 Qwen3 1.7b Q8
7:00 Qwen3 4b Q4
8:20 Qwen3 4b FP16
10:00 Qwen3 8b Q4
11:30 Qwen3 8b FP16
13:45 Qwen3 14b Q4
16:35 Qwen3 14b Q8
19:30 Qwen3coder 30b Q4
24:00 DeepseekR1 1.5b Q4
24:40 DeepseekR1 7b Q4
26:05 DeepseekR1 14b Q4
27:45 DeepseekR1 32b Q4
29:15 DeepseekCoder 33b Q4
31:35 DeepseekCoderV2 16b Q4
33:15 Summary

Видео Local AI Speed Test: Qwen3, Llama, GPT-OSS and Deepseek model tested канала InfraSec

AI LocalAI LLMs Nvidia Nvidia Tesla P100 Ollama Openwebui

Комментарии отсутствуют

Информация о видео

6 января 2026 г. 3:05:59

00:33:28

InfraSec

Теги

Правообладателям

Жалоба на материал Недопустимый материал Нарушение авторских прав

Комментарии

Другие видео канала

Local AI Speed Test: Qwen3, Llama, GPT-OSS and Deepseek model tested

Llama 3.1 8b local AI speed test. #localai , #ollama , #openwebui , #nvidia , #ai , #llm

Qwen3coder 30b Q4 speed test. #ai #coding #localai #nvidia #code #llm #programming #ollama #python

Deepseek R1 14b speed test on local AI server. #ai #localai #nvidia #llm

Deepseek coder V2 16b Q4 Speed test on local ai server. #ai #localai #coding #nvidia #llm #ollama

Local AI vs Chat GPT speed test. #ai #localai #chatgpt #nvidia #speedtest #private #privacy

Qwen3 4b Q4 Speed test local AI server. #ai #llm #localai #nvidia #ollama #openwebui #chatgpt

Llama2 uncensored speed test. #localai , #ollama , #openwebui , #nvidia , #ai , #llm

Qwen3 1.7b Q8 speed test local AI server. #ai #llm #localai #nvidia #ollama #openwebui

Deepseek coder 33b Q4 Speed test on local ai servee #ai #llm #ollama #nvidia #openwebui

Llama 3.2 3b Q5 Speed test. #localai , #ollama , #openwebui , #nvidia , #ai , #llm #chatgpt

Qwen3 14b Q4 Speed test on local AI server. #ai #llm #localai #nvidia #ollama #openwebui #chatgpt

Deepseek R1 32b Q4speed test on local ai server. #ai #localai #nvidia #llm

OSDATA virus: a look at the code + fix

Deepseek R1 7b Q4 Speed test on local AI server. #ai #localai #nvidia #llm

My first computer virus: a quick look

Qwen3 8b FP16 Speed test on local AI server. #ai #llm #localai #nvidia #ollama #openwebui #chatgpt

Local ai VS ChatGPT speed test. GPT:OSS 20b vs GPT 5, 1st part. #ai #chatgpt #localai #nvidia #llm

Qwen3 14b Q8 speed test on local AI server. #ai #coding #localai #windows #nvidia #code #llm #ollama

Qwen3 8b Q4 Speed test on local AI server. #ai #llm #localai #nvidia #ollama #openwebui #chatgpt

GPT-OSS Speedtest on my Homemade AI server. #localai , #ollama , #openwebui , #nvidia , #ai , #llm