TEST #1805 RESULTS
11/15/2025 - 10:16 PM
ACCELERATOR
MODEL
37.7
tokens/s
generation
3.09
sec
time to first token
383
tokens/s
prompt
167
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
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:32:41 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
452
tokens/s
40.5
tokens/s
2.29
sec
pp4096+tg256
426
tokens/s
30.1
tokens/s
9.66
sec
pp2048+tg256
444
tokens/s
36.1
tokens/s
4.64
sec
pp2048+tg768
444
tokens/s
35.2
tokens/s
4.64
sec
pp1024+tg1024
446
tokens/s
38.5
tokens/s
2.32
sec
pp1280+tg3072
446
tokens/s
34.0
tokens/s
2.89
sec
pp384+tg1152
438
tokens/s
41.0
tokens/s
901
ms
pp64+tg1024
276
tokens/s
42.7
tokens/s
255
ms
pp16+tg1536
72
tokens/s
41.6
tokens/s
244
ms