TEST #4036 RESULTS
08/17/2026 - 3:38 AM
ACCELERATOR
MODEL
30.6
tokens/s
generation
4.13
sec
time to first token
300
tokens/s
prompt
131
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.5.0: Tue Jun 9 22:28:34 PDT 2026; root:xnu-12377.121.10~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
339
tokens/s
33.5
tokens/s
3.05
sec
pp4096+tg256
313
tokens/s
23.8
tokens/s
13.13
sec
pp2048+tg256
330
tokens/s
29.1
tokens/s
6.24
sec
pp2048+tg768
331
tokens/s
28.4
tokens/s
6.23
sec
pp1024+tg1024
338
tokens/s
31.2
tokens/s
3.06
sec
pp1280+tg3072
334
tokens/s
27.3
tokens/s
3.87
sec
pp384+tg1152
330
tokens/s
33.4
tokens/s
1.19
sec
pp64+tg1024
274
tokens/s
34.9
tokens/s
261
ms
pp16+tg1536
115
tokens/s
34.1
tokens/s
166
ms