TEST #1895 RESULTS
12/01/2025 - 9:37 AM
ACCELERATOR
MODEL
11.7
tokens/s
generation
10.74
sec
time to first token
121
tokens/s
prompt
51
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Aug 11 21:16:30 PDT 2025; root:xnu-11417.140.69.701.11~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
131
tokens/s
13.2
tokens/s
7.86
sec
pp4096+tg256
119
tokens/s
10.0
tokens/s
34.65
sec
pp2048+tg256
127
tokens/s
11.4
tokens/s
16.19
sec
pp2048+tg768
127
tokens/s
11.1
tokens/s
16.23
sec
pp1024+tg1024
131
tokens/s
11.6
tokens/s
7.88
sec
pp1280+tg3072
128
tokens/s
10.7
tokens/s
10.10
sec
pp384+tg1152
137
tokens/s
12.2
tokens/s
2.86
sec
pp64+tg1024
137
tokens/s
12.7
tokens/s
527
ms
pp16+tg1536
54
tokens/s
12.4
tokens/s
361
ms