TEST #1696 RESULTS
10/24/2025 - 10:33 PM
ACCELERATOR
MODEL
32.7
tokens/s
generation
3.51
sec
time to first token
352
tokens/s
prompt
149
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
64GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Wed Sep 17 21:41:26 PDT 2025; root:xnu-12377.1.9~141/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
410
tokens/s
35.9
tokens/s
2.52
sec
pp4096+tg256
373
tokens/s
25.0
tokens/s
11.02
sec
pp2048+tg256
399
tokens/s
30.9
tokens/s
5.16
sec
pp2048+tg768
400
tokens/s
30.0
tokens/s
5.15
sec
pp1024+tg1024
386
tokens/s
33.5
tokens/s
2.68
sec
pp1280+tg3072
355
tokens/s
28.8
tokens/s
3.63
sec
pp384+tg1152
373
tokens/s
35.9
tokens/s
1.06
sec
pp64+tg1024
339
tokens/s
37.8
tokens/s
214
ms
pp16+tg1536
131
tokens/s
36.7
tokens/s
146
ms