TEST #561 RESULTS
04/08/2025 - 6:44 AM
ACCELERATOR
MODEL
119
tokens/s
generation
569
ms
time to first token
2126
tokens/s
prompt
763
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
24GB
OS
Darwin
Kernel Release
24.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.2.0: Fri Dec 6 19:03:40 PST 2024; root:xnu-11215.61.5~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2659
tokens/s
134
tokens/s
393
ms
pp4096+tg256
2180
tokens/s
77.9
tokens/s
1.89
sec
pp2048+tg256
2487
tokens/s
107
tokens/s
833
ms
pp2048+tg768
2495
tokens/s
102
tokens/s
830
ms
pp1024+tg1024
2539
tokens/s
121
tokens/s
411
ms
pp1280+tg3072
2575
tokens/s
95.9
tokens/s
505
ms
pp384+tg1152
2528
tokens/s
138
tokens/s
158
ms
pp64+tg1024
1304
tokens/s
151
tokens/s
55
ms
pp16+tg1536
370
tokens/s
143
tokens/s
49
ms