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.
| Facet | Apple M5 Pro | NVIDIA GB10 |
|---|---|---|
| Model | Qwen3-0.6B | Qwen3-0.6B-cuda-q4, Qwen3-0.6B-cuda-q4mix, Qwen3-0.6B-cuda-q8, Qwen3-0.6B-Q4 |
| Runtime | BaseRT, llama.cpp | BaseRT |
| Runtime version | BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da) | BaseRT 0.2.6, BaseRT 0.3.0 |
| Quantisation | Q4, Q4_K_M, Q8, Q8_0 | Q4 |
| Backend | BLAS + Metal, Metal | CUDA |
| Conditioning | runtime_native_warmup, warmup_only | warmup_only |
| Decode workload | TG128, TG128 @ 1 ctx | TG128 @ 1 ctx |
| Harness schema | basert-benchmark-harness/1, computearena-measurements/1 | basert-benchmark-harness/1 |
Each row is a configuration present on both sides. Values are per-cell medians; ratios read Apple M5 Pro relative to NVIDIA GB10.
| Configuration | Decode A | Decode B | Ratio | Prefill A | Prefill B | Ratio | Runs A / B |
|---|---|---|---|---|---|---|---|
Qwen3-0.6B-cuda-q8 BaseRTQ4 | 512.0 | 434.6 | 1.18× | 20,603 | 49,677 | 0.41× | 3 / 6 |
Top 10 of 10 runs by decode throughput.
| Model / format | Chip / backend | Decode | Prefill | Contributor | Date | Report |
|---|---|---|---|---|---|---|
basecompute/Qwen3-0.6B BaseRT 0.2.4Q4 | Apple M5 Pro Metal | 516.8 TG128 | 20,778 PP512 | arki05 | View Benchmark | |
basecompute/Qwen3-0.6B BaseRT 0.2.4Q4 | Apple M5 Pro Metal | 512.0 TG128 | 20,603 PP512 | arki05 | View Benchmark | |
basecompute/Qwen3-0.6B BaseRT 0.2.5Q4 | Apple M5 Pro Metal | 481.5 TG128 @ 1 ctx | 19,595 PP512 | isu | View Benchmark | |
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M | Apple M5 Pro BLAS + Metal | 358.3 TG128 | 14,509 PP512 | arki05 | View Benchmark | |
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M | Apple M5 Pro BLAS + Metal | 358.1 TG128 | 14,344 PP512 | arki05 | View Benchmark | |
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M | Apple M5 Pro BLAS + Metal | 356.2 TG128 | 14,552 PP512 | arki05 | View Benchmark | |
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8 | Apple M5 Pro Metal | 350.2 TG128 | 20,537 PP512 | arki05 | View Benchmark | |
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8 | Apple M5 Pro Metal | 349.8 TG128 | 20,366 PP512 | arki05 | View Benchmark | |
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8 | Apple M5 Pro Metal | 311.0 TG128 | 18,474 PP512 | arki05 | View Benchmark | |
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q8_0 | Apple M5 Pro BLAS + Metal | 283.0 TG128 | 14,942 PP512 | arki05 | View Benchmark |
Top 6 of 6 runs by decode throughput.
| Model / format | Chip / backend | Decode | Prefill | Contributor | Date | Report |
|---|---|---|---|---|---|---|
Qwen3-0.6B-Q4 BaseRT 0.2.6Q4 | NVIDIA GB10 CUDA | 458.8 TG128 @ 1 ctx | 20,970 PP512 | basecompute | View Benchmark | |
Qwen3-0.6B-cuda-q4 BaseRT 0.2.6Q4 | NVIDIA GB10 CUDA | 456.1 TG128 @ 1 ctx | 52,750 PP512 | basecompute | View Benchmark | |
Qwen3-0.6B-Q4 BaseRT 0.3.0Q4 | NVIDIA GB10 CUDA | 456.0 TG128 @ 1 ctx | 21,115 PP512 | basecompute | View Benchmark | |
Qwen3-0.6B-cuda-q4mix BaseRT 0.2.6Q4 | NVIDIA GB10 CUDA | 413.2 TG128 @ 1 ctx | 49,865 PP512 | basecompute | View Benchmark | |
Qwen3-0.6B-cuda-q8 BaseRT 0.2.6Q4 | NVIDIA GB10 CUDA | 315.8 TG128 @ 1 ctx | 51,373 PP512 | basecompute | View Benchmark | |
Qwen3-0.6B-cuda-q8 BaseRT 0.3.0Q4 | NVIDIA GB10 CUDA | 309.4 TG128 @ 1 ctx | 49,488 PP512 | basecompute | View Benchmark |