TEST #1246 RESULTS
07/23/2025 - 6:14 PM
ACCELERATOR
MODEL
90.8
tokens/s
generation
904
ms
time to first token
1316
tokens/s
prompt
509
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 6P+4E
RAM
16GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Fri Jul 11 23:59:33 PDT 2025; root:xnu-12377.0.154.0.2~26/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1627
tokens/s
105
tokens/s
639
ms
pp4096+tg256
1402
tokens/s
60.9
tokens/s
2.94
sec
pp2048+tg256
1567
tokens/s
83.0
tokens/s
1.32
sec
pp2048+tg768
1571
tokens/s
79.3
tokens/s
1.32
sec
pp1024+tg1024
1571
tokens/s
92.6
tokens/s
662
ms
pp1280+tg3072
1555
tokens/s
73.5
tokens/s
833
ms
pp384+tg1152
1429
tokens/s
103
tokens/s
277
ms
pp64+tg1024
877
tokens/s
113
tokens/s
81
ms
pp16+tg1536
245
tokens/s
108
tokens/s
73
ms