Archive · Mac (slobodans-macbook-air) · hf-chinchilla. Originally rendered 2026-05-04. Re-hosted from MyServers on 2026-05-06. Methodology and harness conventions may differ from what we use today; see /methodology.html for current standards. ← back to all benchmarks

HF Chinchilla Benchmark - hf-chinchilla-local-mac-20260504T100034Z

- Timestamp (UTC): 2026-05-04T10:00:34Z - Device: cpu - Python: 3.11.15 (main, Mar 3 2026, 15:47:15) [Clang 21.1.4 ] - Torch: 2.11.0 - Transformers: 5.7.0 - Tokenizer: mistralai/Mistral-7B-v0.1

Model Summary

| Model | Avg load (s) | Avg gen latency (s) | Avg tok/s | Prompt runs | |---|---:|---:|---:|---:| | mlnomad/yatnmn-softplus-d22-chinchilla-1B-pytorch | 0.945 | 55.821 | 0.287 | 1 | | mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch | 1.046 | 1.376 | 11.630 | 1 |

Notes

- Each prompt was run multiple times with sampling enabled. - See `results.json` for per-run prompt outputs and raw timings.

Raw data: GitHub archive · Source: ~/Documents/MyServers/instances/slobodans-macbook-air/reports/hf-chinchilla-benchmarks/hf-chinchilla-local-mac-20260504T100034Z/