1 3 494

Rsln Mtvv

Rsln

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

bartowski/Qwen2.5-14B-Instruct-1M-GGUF

liked a model 3 days ago

bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF

liked a model 4 days ago

koboldcpp/tts

View all activity

Organizations

None yet

Rsln's activity

liked 2 models 3 days ago

bartowski/Qwen2.5-14B-Instruct-1M-GGUF

Text Generation • Updated 5 days ago • 5.18k • 23

bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF

Text Generation • Updated 9 days ago • 1.54M • 116

liked 3 models 4 days ago

reacted to mitkox's post with 👍 6 days ago

Post

2054

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.