TEST #1939 RESULTS
12/14/2025 - 5:47 PM
ACCELERATOR
MODEL
17.8
tokens/s
generation
4.28
sec
time to first token
330
tokens/s
prompt
111
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:34 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
406
tokens/s
18.4
tokens/s
2.55
sec
pp4096+tg256
278
tokens/s
14.0
tokens/s
14.83
sec
pp2048+tg256
287
tokens/s
17.8
tokens/s
7.21
sec
pp2048+tg768
319
tokens/s
16.5
tokens/s
6.46
sec
pp1024+tg1024
419
tokens/s
19.0
tokens/s
2.48
sec
pp1280+tg3072
356
tokens/s
16.4
tokens/s
3.63
sec
pp384+tg1152
387
tokens/s
19.8
tokens/s
1.02
sec
pp64+tg1024
341
tokens/s
20.4
tokens/s
219
ms
pp16+tg1536
173
tokens/s
18.0
tokens/s
114
ms