TEST #373 RESULTS
04/06/2025 - 2:02 PM
ACCELERATOR
MODEL
116
tokens/s
generation
590
ms
time to first token
2071
tokens/s
prompt
741
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
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: Wed Mar 12 21:24:54 PDT 2025; root:xnu-11417.101.13~4/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2559
tokens/s
131
tokens/s
408
ms
pp4096+tg256
2094
tokens/s
75.9
tokens/s
1.97
sec
pp2048+tg256
2390
tokens/s
105
tokens/s
866
ms
pp2048+tg768
2394
tokens/s
99.6
tokens/s
865
ms
pp1024+tg1024
2514
tokens/s
118
tokens/s
415
ms
pp1280+tg3072
2508
tokens/s
93.2
tokens/s
518
ms
pp384+tg1152
2338
tokens/s
134
tokens/s
171
ms
pp64+tg1024
1435
tokens/s
147
tokens/s
51
ms
pp16+tg1536
404
tokens/s
139
tokens/s
45
ms