Intel Xeon 6980P Granite Rapids Performance On Linux Over The Past Year https://www.phoronix.com/review/intel-xeon-granite-rapids-ubuntu-2610
Search
5 results for “xeo”
-
Intel Inference Microservices bring tuned LLM inference to Xeon processors through containers, with no manual hardware optimization needed.
#IntelInferenceMicroservices #LLMInference #IntelXeon #vLLM #Kubernetes #Docker #CrescentIsland
https://dailytechnow.com/intel-inference-microservices-xeon/
-
is there a way for forgejo ci when you do "run: | ..." to always do it with "set -xeo pipefail"?
-
Железный сентябрь: от накопителей Unigen на 122 ТБ до архитектуры Arm Ranger и дорожной карты Huawei Ascend
Всем привет, с вами Сергей Ковалёв, менеджер
https://habr.com/ru/companies/selectel/articles/1095216/
#intel_xeon #arm #micron #selectel #amd_epyc #серверные_процессоры #инференс #nvidia_blackwell #иичипы #huawei_ascend
-
Which local model would you recommend for proofreading Spanish articles with Ollama?
I'm looking for a good local model to proofread articles written in Spanish using Ollama, and I'd love to hear about your experiences and recommendations.
My setup is:
RAM: 32 GB
CPU: Intel Xeon E-2280M
GPU: No dedicated GPUMy main use case is proofreading Spanish articles: fixing spelling and grammar mistakes, improving punctuation, and polishing the wording while preserving my writing style. Ideally, the model shouldn't rewrite everything unnecessarily or make up information.
Which Ollama model would you recommend for this use case? I'm particularly interested in Spanish language quality, reasonable performance on CPU-only hardware, and how well it handles longer texts.
If you've tried this on similar hardware, I'd love to hear which model and quantization you use, how fast it runs, and how good the results are in practice.
Thanks in advance! Hopefully, this will also be useful to others running local LLMs on modest hardware.
#selfhosting #ollama