TEST #2930 RESULTS
02/27/2026 - 1:17 PM
ACCELERATOR
MODEL
101
tokens/s
generation
989
ms
time to first token
1293
tokens/s
prompt
508
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 4P+6E
RAM
32GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:49 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8142
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1562
tokens/s
109
tokens/s
665
ms
pp4096+tg256
1208
tokens/s
71.2
tokens/s
3.40
sec
pp2048+tg256
1429
tokens/s
93.6
tokens/s
1.44
sec
pp2048+tg768
1424
tokens/s
90.6
tokens/s
1.45
sec
pp1024+tg1024
1512
tokens/s
103
tokens/s
686
ms
pp1280+tg3072
1493
tokens/s
86.1
tokens/s
867
ms
pp384+tg1152
1462
tokens/s
113
tokens/s
271
ms
pp64+tg1024
1239
tokens/s
121
tokens/s
59
ms
pp16+tg1536
305
tokens/s
117
tokens/s
60
ms