TEST #2350 RESULTS
01/24/2026 - 2:33 PM
ACCELERATOR
MODEL
57.0
tokens/s
generation
1.58
sec
time to first token
819
tokens/s
prompt
309
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
1001
tokens/s
64.0
tokens/s
1.04
sec
pp4096+tg256
731
tokens/s
37.8
tokens/s
5.63
sec
pp2048+tg256
908
tokens/s
51.8
tokens/s
2.28
sec
pp2048+tg768
914
tokens/s
49.7
tokens/s
2.26
sec
pp1024+tg1024
1000
tokens/s
58.3
tokens/s
1.04
sec
pp1280+tg3072
966
tokens/s
46.3
tokens/s
1.34
sec
pp384+tg1152
997
tokens/s
65.2
tokens/s
399
ms
pp64+tg1024
637
tokens/s
71.7
tokens/s
112
ms
pp16+tg1536
215
tokens/s
67.8
tokens/s
86
ms