Contributors › Yamz-Labs's local-LLM benchmark configs
Yamz-Labs's local-LLM benchmark configs
Every tracked benchmark config measured by Yamz-Labs: 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.
1 configs · 1 models · 39 stars · 30 tok/s best single-stream · Yamz-Labs on github.
Configs measured by Yamz-Labs
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| GLM-5.3-Flash | Strix Halo | exllamav3 (speculative decode, spec) | 30 tok/s (prefill 613) | 65536 | 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.