Configs › Qwen3.8-27B-DFlash2 on Strix Halo, DGX Spark and Mac: measured tok/s

Qwen3.8-27B-DFlash2 on Strix Halo, DGX Spark and Mac: measured tok/s

Every tracked benchmark config for Qwen3.8-27B-DFlash2 on local hardware: quant, backend, context, tokens per second, source-linked and trust-tiered.

Snapshot 2026-09-16 · 158 configs · 75 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 Qwen3.8-27B-DFlash2

ModelQuantBackendDecodeContextTrustSource
Qwen3.8-27B-DFlash2Q4_K_Mvulkan21.2 tok/s (prefill 211)32768Owner-submittedsource

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