TEST #3270 RESULTS
04/10/2026 - 3:52 AM
ACCELERATOR
MODEL
174
tokens/s
generation
499
ms
time to first token
2410
tokens/s
prompt
944
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 Pro 6P+12E
RAM
64GB
OS
Darwin
Kernel Release
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:33:50 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6050
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3068
tokens/s
193
tokens/s
339
ms
pp4096+tg256
2487
tokens/s
126
tokens/s
1.65
sec
pp2048+tg256
2812
tokens/s
162
tokens/s
734
ms
pp2048+tg768
2816
tokens/s
157
tokens/s
733
ms
pp1024+tg1024
2924
tokens/s
179
tokens/s
355
ms
pp1280+tg3072
2913
tokens/s
149
tokens/s
445
ms
pp384+tg1152
2791
tokens/s
194
tokens/s
142
ms
pp64+tg1024
1439
tokens/s
208
tokens/s
49
ms
pp16+tg1536
438
tokens/s
200
tokens/s
41
ms