675 19 202

Arthur Zucker

ArthurZ

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

mistralai/Mistral-Small-24B-Instruct-2501

new activity 8 days ago

deepseek-ai/DeepSeek-R1:model-00078-of-000163.safetensors not marked safe?

liked a model 8 days ago

microsoft/phi-4

View all activity

Organizations

ArthurZ's activity

liked a model 2 days ago

mistralai/Mistral-Small-24B-Instruct-2501

Text Generation • Updated 4 days ago • 30.1k • • 624

New activity in deepseek-ai/DeepSeek-R1 8 days ago

model-00078-of-000163.safetensors not marked safe?

#80 opened 8 days ago by

aborst

liked a model 8 days ago

microsoft/phi-4

Text Generation • Updated 2 days ago • 474k • 1.68k

updated a model 9 days ago

ArthurZ/Ilama-3.2-1B

Feature Extraction • Updated 9 days ago • 2.68k

upvoted an article 9 days ago

Article

Welcome to Inference Providers on the Hub 🔥

10 days ago

• 257

published a model 9 days ago

ArthurZ/Ilama-3.2-1B

Feature Extraction • Updated 9 days ago • 2.68k

reacted to mitkox's post with 🚀 10 days ago

Post

2164

llama.cpp is 26.8% faster than ollama.
I have upgraded both, and using the same settings, I am running the same DeepSeek R1 Distill 1.5B on the same hardware. It's an Apples to Apples comparison.

Total duration:
llama.cpp 6.85 sec <- 26.8% faster
ollama 8.69 sec

Breakdown by phase:
Model loading
llama.cpp 241 ms <- 2x faster
ollama 553 ms

Prompt processing
llama.cpp 416.04 tokens/s with an eval time 45.67 ms <- 10x faster
ollama 42.17 tokens/s with an eval time of 498 ms

Token generation
llama.cpp 137.79 tokens/s with an eval time 6.62 sec <- 13% faster
ollama 122.07 tokens/s with an eval time 7.64 sec

llama.cpp is LLM inference in C/C++; ollama adds abstraction layers and marketing.

Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.