Compare
Loading community benchmarks…
Loading community benchmarks…
Put two chips, runtimes, or runtime versions side by side. Everything else is held fixed or called out, so a ratio is worth exactly what the matched runs say.
Ratios read side A relative to side B. Geometric mean over 1 like-for-like pair.
Everything else matches: model, quantisation, backend, protocol, and workload are the same on both sides.
Each row is a configuration present on both sides. Values are per-cell medians; ratios read Apple M1 Max relative to Apple M3 Ultra.
| Configuration | Decode A | Decode B | Ratio | Prefill A | Prefill B | Ratio | Runs A / B |
|---|---|---|---|---|---|---|---|
Qwen3.5-2B-Q4 BaseRTQ4 | 188.6 | 313.4 | 0.60× | 2,105 | 5,478 | 0.38× | 1 / 1 |
Top 1 of 1 run by decode throughput.
| Model / format | Chip / backend | Decode | Prefill | Contributor | Date | Report |
|---|---|---|---|---|---|---|
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4 | Apple M1 Max Metal | 188.6 TG128 @ 1 ctx | 2,105 PP512 | basecompute | View Benchmark |
Top 1 of 1 run by decode throughput.
| Model / format | Chip / backend | Decode | Prefill | Contributor | Date | Report |
|---|---|---|---|---|---|---|
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4 | Apple M3 Ultra Metal | 313.4 TG128 @ 1 ctx | 5,478 PP512 | basecompute | View Benchmark |