Contributors › jaedync's local-LLM benchmark configs
jaedync's local-LLM benchmark configs
Every tracked benchmark config measured by jaedync: model, quant, backend, tokens per second, source-linked and trust-tiered.
Snapshot 2026-10-29 · 413 configs on AI boxes and 288 on GPU cards · 121 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
1 configs · 1 models · 7 stars · 57.5 tok/s best single-stream · jaedync on github.
Configs measured by jaedync
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | Strix Halo | crucible (speculative decode, mtp) | 57.5 tok/s (prefill 1561) | 32768 | 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.