TEST #828 RESULTS
05/05/2025 - 10:39 PM
ACCELERATOR
MODEL
32.1
tokens/s
generation
3.99
sec
time to first token
306
tokens/s
prompt
135
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
64GB
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
348
tokens/s
34.6
tokens/s
2.97
sec
pp4096+tg256
328
tokens/s
25.2
tokens/s
12.55
sec
pp2048+tg256
341
tokens/s
30.6
tokens/s
6.05
sec
pp2048+tg768
341
tokens/s
29.8
tokens/s
6.05
sec
pp1024+tg1024
346
tokens/s
32.8
tokens/s
2.99
sec
pp1280+tg3072
344
tokens/s
28.7
tokens/s
3.75
sec
pp384+tg1152
345
tokens/s
35.0
tokens/s
1.14
sec
pp64+tg1024
266
tokens/s
36.6
tokens/s
267
ms
pp16+tg1536
98
tokens/s
35.7
tokens/s
189
ms