TEST #1763 RESULTS
11/08/2025 - 8:22 PM
ACCELERATOR
MODEL
68.2
tokens/s
generation
1.40
sec
time to first token
944
tokens/s
prompt
358
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
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Aug 11 21:16:33 PDT 2025; root:xnu-11417.140.69.701.11~1/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1127
tokens/s
76.7
tokens/s
921
ms
pp4096+tg256
821
tokens/s
48.3
tokens/s
5.01
sec
pp2048+tg256
1005
tokens/s
63.6
tokens/s
2.05
sec
pp2048+tg768
1009
tokens/s
61.1
tokens/s
2.05
sec
pp1024+tg1024
1112
tokens/s
70.1
tokens/s
935
ms
pp1280+tg3072
1101
tokens/s
56.5
tokens/s
1.18
sec
pp384+tg1152
1146
tokens/s
76.6
tokens/s
348
ms
pp64+tg1024
862
tokens/s
81.5
tokens/s
85
ms
pp16+tg1536
314
tokens/s
79.3
tokens/s
62
ms