TEST #1402 RESULTS
08/20/2025 - 12:29 PM
ACCELERATOR
MODEL
22.0
tokens/s
generation
6.09
sec
time to first token
205
tokens/s
prompt
91
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
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 Jul 14 11:30:29 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
229
tokens/s
23.8
tokens/s
4.52
sec
pp4096+tg256
212
tokens/s
17.2
tokens/s
19.34
sec
pp2048+tg256
224
tokens/s
21.1
tokens/s
9.20
sec
pp2048+tg768
224
tokens/s
20.4
tokens/s
9.19
sec
pp1024+tg1024
229
tokens/s
21.8
tokens/s
4.52
sec
pp1280+tg3072
227
tokens/s
19.6
tokens/s
5.68
sec
pp384+tg1152
228
tokens/s
24.0
tokens/s
1.72
sec
pp64+tg1024
198
tokens/s
25.1
tokens/s
360
ms
pp16+tg1536
78
tokens/s
24.5
tokens/s
242
ms