TEST #1247 RESULTS
07/23/2025 - 6:30 PM
ACCELERATOR
MODEL
25.0
tokens/s
generation
5.43
sec
time to first token
229
tokens/s
prompt
102
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 6P+4E
RAM
16GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Fri Jul 11 23:59:33 PDT 2025; root:xnu-12377.0.154.0.2~26/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
257
tokens/s
27.1
tokens/s
4.03
sec
pp4096+tg256
238
tokens/s
19.7
tokens/s
17.25
sec
pp2048+tg256
251
tokens/s
23.8
tokens/s
8.20
sec
pp2048+tg768
251
tokens/s
23.3
tokens/s
8.19
sec
pp1024+tg1024
256
tokens/s
25.6
tokens/s
4.04
sec
pp1280+tg3072
254
tokens/s
22.3
tokens/s
5.07
sec
pp384+tg1152
255
tokens/s
27.2
tokens/s
1.54
sec
pp64+tg1024
214
tokens/s
28.5
tokens/s
333
ms
pp16+tg1536
86
tokens/s
27.8
tokens/s
220
ms