Hardware1
Apple M4 Pro
1 runBest decode · TG128
74.7tok/s
Best prefill · PP512
757tok/s
Badges2
Record1
Pioneer1
Decode record
Fastest result in a tested configuration
Record
First run
Submitted a benchmark report
Pioneer
Submission1
Sort by
Order
Prefill size
1 submission · PP512 selected
| Model / runtime / format | Device | Backend | Report | |||
|---|---|---|---|---|---|---|
Gemma-4 26B-A4B IT (smart Q4_0, QAT-lossless) llama.cppQ4_0 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | BLAS + Metal | 74.7 tok/s TG128 | 757 tok/s PP512 |