Contributors › petr567's local-LLM benchmark configs
petr567's local-LLM benchmark configs
Every tracked benchmark config measured by petr567: 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.
2 configs · 2 models · 182.1 tok/s best single-stream · petr567 on huggingface.
Configs measured by petr567
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| LFM2.5-2.6B | Strix Halo | Q4_K_M | llama.cpp/vulkan (speculative decode, ngram) | 182.1 tok/s | 8192 | Extracted, source-linked | source |
| Ornith-1.0-35B | Strix Halo | Q4_K_M | llama.cpp/vulkan (speculative decode, mtp-ngram) | 70.3 tok/s | 62630 | 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.