Contributors › shamily's local-LLM benchmark configs
shamily's local-LLM benchmark configs
Every tracked benchmark config measured by shamily: 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 · 2 models · 69.9 tok/s best single-stream · shamily on github.
Configs measured by shamily
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| gemma-4-26B-A4B-it | DGX Spark | Q4_K_M | llama.cpp/cuda | 69.9 tok/s (prefill 2657) | Structured table | source | |
| Gemma-4-31B-IT | DGX Spark | Q4_K_M | llama.cpp/cuda | 11 tok/s (prefill 743) | 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.