TEST #3106 RESULTS
03/18/2026 - 6:30 AM
ACCELERATOR
MODEL
229
tokens/s
generation
322
ms
time to first token
3621
tokens/s
prompt
1371
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
4816
tokens/s
249
tokens/s
217
ms
pp4096+tg256
3911
tokens/s
171
tokens/s
1.05
sec
pp2048+tg256
4439
tokens/s
217
tokens/s
466
ms
pp2048+tg768
4585
tokens/s
210
tokens/s
451
ms
pp1024+tg1024
4445
tokens/s
235
tokens/s
234
ms
pp1280+tg3072
4508
tokens/s
201
tokens/s
288
ms
pp384+tg1152
3881
tokens/s
253
tokens/s
103
ms
pp64+tg1024
1577
tokens/s
267
tokens/s
44
ms
pp16+tg1536
424
tokens/s
260
tokens/s
41
ms