family member

Llama-3.2-1B-Instruct-Q4_K_M-GGUF

1 build of Llama-3.2-1B-Instruct-Q4_K_M-GGUF measured on real machines — different packagers, precisions and engines, each a different file with its own numbers. The best each engine proved is first; every build has its own page with the machines and signatures behind it.

on ollama · 1 build

no context proved on this engine yet

11.3 tok/s peak, by hugging-quants Q4_K_M

proved by at least one build: Structured output · Sustained output

build	publisher	precision	engine	whose work	context proved	best tok/s	machines
hf.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF:Q4_K_M	hugging-quants	Q4_K_M	ollama	derivative	—	11.3	1