TEST #811 RESULTS
05/04/2025 - 10:05 AM
ACCELERATOR
MODEL
22.0
tokens/s
generation
6.09
sec
time to first token
205
tokens/s
prompt
90
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
RAM
32GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:33:47 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
228
tokens/s
23.8
tokens/s
4.53
sec
pp4096+tg256
212
tokens/s
17.2
tokens/s
19.35
sec
pp2048+tg256
224
tokens/s
20.9
tokens/s
9.20
sec
pp2048+tg768
224
tokens/s
20.4
tokens/s
9.20
sec
pp1024+tg1024
228
tokens/s
22.4
tokens/s
4.54
sec
pp1280+tg3072
227
tokens/s
19.6
tokens/s
5.69
sec
pp384+tg1152
228
tokens/s
24.0
tokens/s
1.72
sec
pp64+tg1024
192
tokens/s
25.1
tokens/s
371
ms
pp16+tg1536
79
tokens/s
24.5
tokens/s
240
ms