TEST #1894 RESULTS
12/01/2025 - 7:58 AM
ACCELERATOR
MODEL
76.0
tokens/s
generation
1.18
sec
time to first token
1114
tokens/s
prompt
416
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
32GB
OS
Darwin
Kernel Release
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:32:56 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1337
tokens/s
85.4
tokens/s
778
ms
pp4096+tg256
981
tokens/s
55.7
tokens/s
4.19
sec
pp2048+tg256
1202
tokens/s
69.7
tokens/s
1.72
sec
pp2048+tg768
1207
tokens/s
69.2
tokens/s
1.71
sec
pp1024+tg1024
1329
tokens/s
78.8
tokens/s
782
ms
pp1280+tg3072
1301
tokens/s
64.8
tokens/s
996
ms
pp384+tg1152
1353
tokens/s
84.6
tokens/s
295
ms
pp64+tg1024
964
tokens/s
88.4
tokens/s
79
ms
pp16+tg1536
348
tokens/s
87.3
tokens/s
57
ms