Hardware3

Apple M5 Pro

7 runs
Best decode · TG128 @ 1 ctx
481.5tok/s
Best prefill · PP512
19,595tok/s

AMD Ryzen 5 7600 6-Core Processor

1 run
Best decode · TG128
16.2tok/s
Best prefill · PP512
78tok/s

Apple M1 Pro

1 run
Best decode · TG128 @ 1 ctx
268.8tok/s
Best prefill · PP512
2,847tok/s
Badges6
Record1
Pioneer1
Volume1
Coverage3
3 decode records
Fastest result in a tested configuration
Record
First run
Submitted a benchmark report
Pioneer
5 runs
Contributor
Volume
Model explorer
4 models covered
Coverage
Hardware explorer
3 devices covered
Coverage
Multi-backend
BLAS,MTL + CPU + metal
Coverage
Submissions9
Sort by
Order
Prefill size
9 submissions · PP512 selected
Model / runtime / formatDeviceBackendReport
basecompute/Qwen3-0.6B
BaseRTQ4· default-q4
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 M1 ProMetal
268.8 tok/s
TG128 @ 1 ctx
2,847 tok/s
PP512
basecompute/Qwen3-8B
BaseRTQ4· default-q4
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 M5 ProMetal
59.7 tok/s
TG128 @ 1 ctx
1,762 tok/s
PP512
basecompute/Qwen3-0.6B
BaseRTQ4· default-q4
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 M5 ProMetal
481.5 tok/s
TG128 @ 1 ctx
19,595 tok/s
PP512
Qwen3.5-4B
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.
AMD Ryzen 5 7600 6-Core ProcessorCPU
16.2 tok/s
TG128
78 tok/s
PP512
basecompute/Qwen3-8B
BaseRTQ4· default-q4
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 M5 ProMetal
59.7 tok/s
TG128
1,761 tok/s
PP512
basecompute/Qwen3-8B
BaseRTQ4· default-q4
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 M5 ProMetal
58.2 tok/s
TG128
1,758 tok/s
PP512
Qwen3-4B
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 M5 ProBLAS + Metal
93.6 tok/s
TG128
2,705 tok/s
PP512
basecompute/Qwen3-8B
BaseRTQ4· default-q4
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 M5 ProMetal
60.6 tok/s
TG128
1,763 tok/s
PP512
basecompute/Qwen3-8B
BaseRTQ4· default-q4
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 M5 ProMetal
56.9 tok/s
TG128
1,707 tok/s
PP512