Contributors › gufo-org's local-LLM benchmark configs
gufo-org's local-LLM benchmark configs
Every tracked benchmark config measured by gufo-org: model, quant, backend, tokens per second, source-linked and trust-tiered.
Snapshot 2026-10-15 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
5 configs · 3 models · 736 stars · 121.2 tok/s best single-stream · gufo-org on github.
Configs measured by gufo-org
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Qwen3.8-27B | Strix Halo | Q4_K_XL | gufo (speculative decode, dflash2) | 36.3 tok/s (prefill 607.3) | Extracted, source-linked | source | |
| Qwen3.8-Flash-Next | Strix Halo | UD-Q4_K_XL | gufo (speculative decode, mtp) | 33.4 tok/s (prefill 1689.4) | Extracted, source-linked | source |
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.