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 2 like-for-like pairs.
| Facet | Apple M5 Pro | Apple M1 Max |
|---|---|---|
| Model | gemma-4-E4B-it, Gemma-4-E4B-It | gemma-4-E4B-it-Q4, gemma-4-E4B-it-Q8 |
| Runtime | BaseRT, llama.cpp | BaseRT |
| Runtime version | BaseRT 0.2.4, llama.cpp b10809 (5266f24da) | BaseRT 0.2.6, BaseRT 0.3.0 |
| Quantisation | Q4, Q4_K_M, Q8, Q8_0 | Q4, Q8 |
| Backend | BLAS + Metal, Metal | Metal |
| Conditioning | runtime_native_warmup, warmup_only | warmup_only |
| Decode workload | TG128 | 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 Apple M1 Max.
| Configuration | Decode A | Decode B | Ratio | Prefill A | Prefill B | Ratio | Runs A / B |
|---|---|---|---|---|---|---|---|
gemma-4-E4B-it BaseRTQ4 | 82.3 | 75.5 | 1.09× | 4,646 | 1,388 | 3.35× | 2 / 2 |
gemma-4-E4B-it BaseRTQ8 | 51.2 | 51.6 | 0.99× | 4,476 | 1,369 | 3.27× | 2 / 2 |
Top 7 of 7 runs by decode throughput.
| Model / format | Chip / backend | Decode | Prefill | Contributor | Date | Report |
|---|---|---|---|---|---|---|
basecompute/gemma-4-E4B-it BaseRT 0.2.4Q4 | Apple M5 Pro Metal | 82.6 TG128 | 4,656 PP512 | arki05 | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRT 0.2.4Q4 | Apple M5 Pro Metal | 81.9 TG128 | 4,636 PP512 | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cpp b10809 (5266f24da)Q4_K_M | Apple M5 Pro BLAS + Metal | 72.1 TG128 | 2,263 PP512 | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cpp b10809 (5266f24da)Q4_K_M | Apple M5 Pro BLAS + Metal | 69.4 TG128 | 2,235 PP512 | arki05 | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRT 0.2.4Q8 | Apple M5 Pro Metal | 51.3 TG128 | 4,490 PP512 | arki05 | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRT 0.2.4Q8 | Apple M5 Pro Metal | 51.0 TG128 | 4,462 PP512 | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cpp b10809 (5266f24da)Q8_0 | Apple M5 Pro BLAS + Metal | 47.9 TG128 | 2,346 PP512 | arki05 | View Benchmark |
Top 4 of 4 runs by decode throughput.
| Model / format | Chip / backend | Decode | Prefill | Contributor | Date | Report |
|---|---|---|---|---|---|---|
gemma-4-E4B-it-Q4 BaseRT 0.2.6Q4 | Apple M1 Max Metal | 75.9 TG128 @ 1 ctx | 1,394 PP512 | basecompute | View Benchmark | |
gemma-4-E4B-it-Q4 BaseRT 0.3.0Q4 | Apple M1 Max Metal | 75.1 TG128 @ 1 ctx | 1,383 PP512 | basecompute | View Benchmark | |
gemma-4-E4B-it-Q8 BaseRT 0.2.6Q8 | Apple M1 Max Metal | 52.0 TG128 @ 1 ctx | 1,368 PP512 | basecompute | View Benchmark | |
gemma-4-E4B-it-Q8 BaseRT 0.3.0Q8 | Apple M1 Max Metal | 51.3 TG128 @ 1 ctx | 1,369 PP512 | basecompute | View Benchmark |