TEST #3181 RESULTS
03/25/2026 - 12:01 AM
ACCELERATOR
MODEL
230
tokens/s
generation
317
ms
time to first token
3727
tokens/s
prompt
1393
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 Max 6P+12E
RAM
36GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:54:38 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T6050
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4840
tokens/s
251
tokens/s
216
ms
pp4096+tg256
3933
tokens/s
172
tokens/s
1.05
sec
pp2048+tg256
4445
tokens/s
217
tokens/s
465
ms
pp2048+tg768
4598
tokens/s
210
tokens/s
450
ms
pp1024+tg1024
4509
tokens/s
235
tokens/s
231
ms
pp1280+tg3072
4544
tokens/s
201
tokens/s
286
ms
pp384+tg1152
4067
tokens/s
254
tokens/s
98
ms
pp64+tg1024
1763
tokens/s
269
tokens/s
40
ms
pp16+tg1536
846
tokens/s
261
tokens/s
22
ms