Contributors › wireframeslayout's local-LLM benchmark configs
wireframeslayout's local-LLM benchmark configs
Every tracked benchmark config measured by wireframeslayout: model, quant, backend, tokens per second, source-linked and trust-tiered.
Snapshot 2026-09-30 · 254 configs · 116 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 · 52.9 tok/s best single-stream · wireframeslayout on github.
Configs measured by wireframeslayout
| Model | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|
| gpt-oss-120b | MXFP4 | llama.cpp/vulkan | 52.9 tok/s | 128 | Extracted, source-linked | source |
| gpt-oss-120b | MXFP4 | llama.cpp/rocm | 50.2 tok/s | 128 | Extracted, source-linked | source |
More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.