TEST #2598 RESULTS
02/11/2026 - 11:34 AM
ACCELERATOR
MODEL
36.0
tokens/s
generation
2.59
sec
time to first token
503
tokens/s
prompt
191
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
16GB
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 19:32:47 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
607
tokens/s
42.5
tokens/s
1.71
sec
pp4096+tg256
453
tokens/s
23.4
tokens/s
9.08
sec
pp2048+tg256
526
tokens/s
33.3
tokens/s
3.92
sec
pp2048+tg768
557
tokens/s
28.0
tokens/s
3.70
sec
pp1024+tg1024
585
tokens/s
36.8
tokens/s
1.78
sec
pp1280+tg3072
589
tokens/s
29.0
tokens/s
2.20
sec
pp384+tg1152
607
tokens/s
41.7
tokens/s
654
ms
pp64+tg1024
434
tokens/s
45.7
tokens/s
171
ms
pp16+tg1536
169
tokens/s
43.3
tokens/s
115
ms