Contributors › pepuscz's local-LLM benchmark configs
pepuscz's local-LLM benchmark configs
Every tracked benchmark config measured by pepuscz: 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.
2 configs · 1 models · 25 stars · 35.7 tok/s best single-stream · pepuscz on github.
Configs measured by pepuscz
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek-V4-Flash-0731 | Strix Halo | UD-IQ3_XXS | llama.cpp/vulkan (speculative decode, dspark) | 35.7 tok/s (prefill 226.8) | 524288 | Structured table | source |
| DeepSeek-V4-Flash-0731 | Strix Halo | rocm (speculative decode, dspark) | 29.6 tok/s (prefill 142.8) | 131072 | Structured table | 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.