TEST #2664 RESULTS
02/15/2026 - 5:18 PM
ACCELERATOR
MODEL
120
tokens/s
generation
575
ms
time to first token
2150
tokens/s
prompt
766
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2632
tokens/s
135
tokens/s
397
ms
pp4096+tg256
2127
tokens/s
76.3
tokens/s
1.94
sec
pp2048+tg256
2458
tokens/s
107
tokens/s
843
ms
pp2048+tg768
2452
tokens/s
104
tokens/s
845
ms
pp1024+tg1024
2573
tokens/s
122
tokens/s
406
ms
pp1280+tg3072
2567
tokens/s
96.5
tokens/s
508
ms
pp384+tg1152
2518
tokens/s
140
tokens/s
159
ms
pp64+tg1024
1522
tokens/s
154
tokens/s
48
ms
pp16+tg1536
504
tokens/s
146
tokens/s
37
ms