TEST #3128 RESULTS
03/20/2026 - 12:47 PM
ACCELERATOR
MODEL
34.0
tokens/s
generation
3.03
sec
time to first token
433
tokens/s
prompt
169
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple A18 Pro 2P+4E
RAM
8GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:56:11 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T8140
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
548
tokens/s
44.2
tokens/s
1.89
sec
pp4096+tg256
430
tokens/s
25.2
tokens/s
9.57
sec
pp2048+tg256
433
tokens/s
32.3
tokens/s
4.76
sec
pp2048+tg768
436
tokens/s
30.7
tokens/s
4.73
sec
pp1024+tg1024
445
tokens/s
33.7
tokens/s
2.33
sec
pp1280+tg3072
446
tokens/s
27.6
tokens/s
2.90
sec
pp384+tg1152
475
tokens/s
36.4
tokens/s
834
ms
pp64+tg1024
500
tokens/s
38.8
tokens/s
149
ms
pp16+tg1536
182
tokens/s
37.3
tokens/s
107
ms