TEST #3323 RESULTS
04/16/2026 - 1:24 AM
ACCELERATOR
MODEL
43.7
tokens/s
generation
3.67
sec
time to first token
341
tokens/s
prompt
159
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 Pro 5P+10E
RAM
48GB
OS
Darwin
Kernel Release
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:33:50 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6050
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
380
tokens/s
46.7
tokens/s
2.71
sec
pp4096+tg256
351
tokens/s
36.0
tokens/s
11.70
sec
pp2048+tg256
370
tokens/s
42.2
tokens/s
5.56
sec
pp2048+tg768
371
tokens/s
41.1
tokens/s
5.55
sec
pp1024+tg1024
380
tokens/s
44.6
tokens/s
2.72
sec
pp1280+tg3072
376
tokens/s
39.9
tokens/s
3.42
sec
pp384+tg1152
376
tokens/s
46.9
tokens/s
1.04
sec
pp64+tg1024
321
tokens/s
48.5
tokens/s
219
ms
pp16+tg1536
140
tokens/s
47.6
tokens/s
134
ms