TEST #3294 RESULTS
04/12/2026 - 1:01 AM
ACCELERATOR
MODEL
14.6
tokens/s
generation
9.64
sec
time to first token
134
tokens/s
prompt
59
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
8GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Fri Feb 27 19:34:43 PST 2026; root:xnu-11417.140.69.709.8~1/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
146
tokens/s
15.1
tokens/s
7.09
sec
pp4096+tg256
132
tokens/s
11.9
tokens/s
31.20
sec
pp2048+tg256
141
tokens/s
14.3
tokens/s
14.55
sec
pp2048+tg768
141
tokens/s
13.6
tokens/s
14.56
sec
pp1024+tg1024
147
tokens/s
14.9
tokens/s
7.01
sec
pp1280+tg3072
145
tokens/s
13.1
tokens/s
8.89
sec
pp384+tg1152
150
tokens/s
15.9
tokens/s
2.61
sec
pp64+tg1024
142
tokens/s
16.5
tokens/s
507
ms
pp16+tg1536
61
tokens/s
16.2
tokens/s
318
ms