TEST #1317 RESULTS
08/05/2025 - 5:03 PM
ACCELERATOR
MODEL
91.5
tokens/s
generation
914
ms
time to first token
1281
tokens/s
prompt
504
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 6P+4E
RAM
32GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:25 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1635
tokens/s
104
tokens/s
636
ms
pp4096+tg256
1389
tokens/s
60.3
tokens/s
2.97
sec
pp2048+tg256
1545
tokens/s
82.4
tokens/s
1.34
sec
pp2048+tg768
1550
tokens/s
78.7
tokens/s
1.33
sec
pp1024+tg1024
1625
tokens/s
93.1
tokens/s
640
ms
pp1280+tg3072
1556
tokens/s
74.0
tokens/s
833
ms
pp384+tg1152
1362
tokens/s
105
tokens/s
290
ms
pp64+tg1024
673
tokens/s
116
tokens/s
103
ms
pp16+tg1536
197
tokens/s
110
tokens/s
89
ms