TEST #1100 RESULTS
06/24/2025 - 9:29 AM
ACCELERATOR
MODEL
20.4
tokens/s
generation
6.87
sec
time to first token
181
tokens/s
prompt
81
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
16GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:49 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
202
tokens/s
22.2
tokens/s
5.12
sec
pp4096+tg256
189
tokens/s
15.8
tokens/s
21.78
sec
pp2048+tg256
198
tokens/s
19.5
tokens/s
10.40
sec
pp2048+tg768
199
tokens/s
18.9
tokens/s
10.35
sec
pp1024+tg1024
203
tokens/s
20.9
tokens/s
5.10
sec
pp1280+tg3072
201
tokens/s
18.2
tokens/s
6.40
sec
pp384+tg1152
202
tokens/s
22.3
tokens/s
1.94
sec
pp64+tg1024
164
tokens/s
23.4
tokens/s
430
ms
pp16+tg1536
70
tokens/s
22.8
tokens/s
269
ms