TEST #1958 RESULTS
12/17/2025 - 1:57 PM
ACCELERATOR
MODEL
32.9
tokens/s
generation
3.42
sec
time to first token
362
tokens/s
prompt
152
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
414
tokens/s
36.0
tokens/s
2.50
sec
pp4096+tg256
375
tokens/s
25.3
tokens/s
10.96
sec
pp2048+tg256
405
tokens/s
31.6
tokens/s
5.09
sec
pp2048+tg768
404
tokens/s
30.3
tokens/s
5.10
sec
pp1024+tg1024
412
tokens/s
33.7
tokens/s
2.51
sec
pp1280+tg3072
395
tokens/s
29.0
tokens/s
3.27
sec
pp384+tg1152
405
tokens/s
36.1
tokens/s
974
ms
pp64+tg1024
316
tokens/s
37.4
tokens/s
233
ms
pp16+tg1536
135
tokens/s
36.9
tokens/s
143
ms