TEST #2758 RESULTS
02/19/2026 - 2:04 PM
ACCELERATOR
MODEL
66.3
tokens/s
generation
1.39
sec
time to first token
931
tokens/s
prompt
354
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 4P+4E
RAM
16GB
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 21:03:25 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1136
tokens/s
76.6
tokens/s
914
ms
pp4096+tg256
839
tokens/s
48.6
tokens/s
4.90
sec
pp2048+tg256
1033
tokens/s
63.4
tokens/s
2.00
sec
pp2048+tg768
1032
tokens/s
61.2
tokens/s
2.00
sec
pp1024+tg1024
1134
tokens/s
70.1
tokens/s
916
ms
pp1280+tg3072
1051
tokens/s
57.6
tokens/s
1.23
sec
pp384+tg1152
1022
tokens/s
72.5
tokens/s
389
ms
pp64+tg1024
822
tokens/s
76.0
tokens/s
90
ms
pp16+tg1536
312
tokens/s
70.9
tokens/s
63
ms