TEST #1135 RESULTS
06/27/2025 - 9:42 AM
ACCELERATOR
MODEL
126
tokens/s
generation
556
ms
time to first token
2065
tokens/s
prompt
776
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
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 19:54:49 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2673
tokens/s
143
tokens/s
390
ms
pp4096+tg256
2331
tokens/s
86.6
tokens/s
1.77
sec
pp2048+tg256
2631
tokens/s
114
tokens/s
787
ms
pp2048+tg768
2562
tokens/s
110
tokens/s
808
ms
pp1024+tg1024
2577
tokens/s
128
tokens/s
405
ms
pp1280+tg3072
2563
tokens/s
105
tokens/s
507
ms
pp384+tg1152
2215
tokens/s
144
tokens/s
180
ms
pp64+tg1024
798
tokens/s
155
tokens/s
86
ms
pp16+tg1536
233
tokens/s
148
tokens/s
74
ms