TEST #832 RESULTS
05/06/2025 - 6:15 AM
ACCELERATOR
MODEL
6.2
tokens/s
generation
15.14
sec
time to first token
84
tokens/s
prompt
33
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 32B - Q8_0
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
64GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:32:50 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
103
tokens/s
6.5
tokens/s
10.13
sec
pp4096+tg256
90
tokens/s
5.5
tokens/s
45.57
sec
pp2048+tg256
84
tokens/s
6.1
tokens/s
24.50
sec
pp2048+tg768
88
tokens/s
6.0
tokens/s
23.52
sec
pp1024+tg1024
88
tokens/s
6.3
tokens/s
11.82
sec
pp1280+tg3072
87
tokens/s
5.9
tokens/s
14.82
sec
pp384+tg1152
88
tokens/s
6.5
tokens/s
4.49
sec
pp64+tg1024
87
tokens/s
6.7
tokens/s
878
ms
pp16+tg1536
39
tokens/s
6.6
tokens/s
554
ms