TEST #176 RESULTS
03/30/2025 - 8:17 PM
ACCELERATOR
MODEL
21.3
tokens/s
generation
6.74
sec
time to first token
185
tokens/s
prompt
84
LocalScore
HOW YOU STACK UP
Explore All ResultsMistral Small 24B Instruct 2501 - Q4_K - Small
SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
OS
Darwin
Kernel Release
24.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.1.0: Thu Nov 14 18:15:21 PST 2024; root:xnu-11215.41.3~13/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
218
tokens/s
22.7
tokens/s
4.74
sec
pp4096+tg256
205
tokens/s
18.7
tokens/s
20.05
sec
pp2048+tg256
194
tokens/s
21.0
tokens/s
10.63
sec
pp2048+tg768
190
tokens/s
20.7
tokens/s
10.83
sec
pp1024+tg1024
206
tokens/s
21.3
tokens/s
5.01
sec
pp1280+tg3072
190
tokens/s
19.7
tokens/s
6.80
sec
pp384+tg1152
207
tokens/s
22.5
tokens/s
1.90
sec
pp64+tg1024
185
tokens/s
22.9
tokens/s
387
ms
pp16+tg1536
71
tokens/s
22.5
tokens/s
266
ms