TEST #2898 RESULTS
02/25/2026 - 5:32 AM
ACCELERATOR
MODEL
48.7
tokens/s
generation
2.11
sec
time to first token
584
tokens/s
prompt
238
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
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 20:48:41 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
666
tokens/s
52.4
tokens/s
1.56
sec
pp4096+tg256
613
tokens/s
38.4
tokens/s
6.71
sec
pp2048+tg256
647
tokens/s
46.2
tokens/s
3.19
sec
pp2048+tg768
647
tokens/s
45.2
tokens/s
3.19
sec
pp1024+tg1024
662
tokens/s
49.8
tokens/s
1.56
sec
pp1280+tg3072
659
tokens/s
43.6
tokens/s
1.96
sec
pp384+tg1152
649
tokens/s
53.3
tokens/s
609
ms
pp64+tg1024
539
tokens/s
55.4
tokens/s
136
ms
pp16+tg1536
171
tokens/s
54.2
tokens/s
110
ms