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
| Model | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|
| Qwen3.8-27B-DFlash2 | Q4_K_M | vulkan | 21.2 tok/s (prefill 211) | 32768 | Owner-submitted | source |
More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.