Contributors › Soulmate-Halo's local-LLM benchmark configs
Soulmate-Halo's local-LLM benchmark configs
Every tracked benchmark config measured by Soulmate-Halo: 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.
3 configs · 2 models · 783 stars · 323.2 tok/s best single-stream · Soulmate-Halo on github.
Configs measured by Soulmate-Halo
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | Strix Halo | NVFP4 | 41.3 tok/s (prefill 273) | Extracted, source-linked | source | ||
| Qwen3.8-Flash-Next | DGX Spark | NVFP4 | 22.3 tok/s (prefill 1117.9) | 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.