Configs › llama-3.2-1b on Strix Halo, DGX Spark and Mac: measured tok/s

llama-3.2-1b on Strix Halo, DGX Spark and Mac: measured tok/s

Every tracked benchmark config for llama-3.2-1b on local hardware: quant, backend, context, tokens per second, source-linked and trust-tiered.

Snapshot 2026-09-30 · 254 configs · 116 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

Measured configs for llama-3.2-1b

ModelQuantBackendDecodeContextTrustSource
llama-3.2-1bMLX-4BITmlx527.7 tok/s (prefill 17477)512Extracted, source-linkedsource
llama-3.2-1bQ4_K_Mllama.cpp439.6 tok/s (prefill 16968)512Extracted, source-linkedsource

More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.