Hardware1

Apple M4 Max

2 runs
Best decode · TG128
31.6tok/s
Best prefill · PP512
243tok/s
Badges3
Record1
Pioneer1
Coverage1
2 decode records
Fastest result in a tested configuration
Record
First run
Submitted a benchmark report
Pioneer
Multi-backend
BLAS,MTL + metal
Coverage
Submissions2
Sort by
Order
Prefill size
2 submissions · PP512 selected
Model / runtime / formatDeviceBackendReport
Qwen3.8-27B
llama.cppQ4_K_M
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 MaxBLAS + Metal
22.9 tok/s
TG128
243 tok/s
PP512
Qwen3.8-27B-Q4
BaseRTQ4
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 MaxMetal
31.6 tok/s
TG128
222 tok/s
PP512