Configs › qwen3-8b on Strix Halo, DGX Spark and Mac: measured tok/s

qwen3-8b on Strix Halo, DGX Spark and Mac: measured tok/s

Every tracked benchmark config for qwen3-8b 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 qwen3-8b

ModelQuantBackendDecodeContextTrustSource
qwen3-8bMLX-4BITmlx110.5 tok/s (prefill 3151)512Extracted, source-linkedsource
qwen3-8bQ4_K_Mllama.cpp97.7 tok/s (prefill 2745)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.