TEST #2213 RESULTS
01/10/2026 - 4:48 AM
ACCELERATOR
MODEL
60.0
tokens/s
generation
1.55
sec
time to first token
837
tokens/s
prompt
319
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
1009
tokens/s
68.2
tokens/s
1.03
sec
pp4096+tg256
746
tokens/s
39.3
tokens/s
5.52
sec
pp2048+tg256
916
tokens/s
54.0
tokens/s
2.25
sec
pp2048+tg768
915
tokens/s
51.5
tokens/s
2.26
sec
pp1024+tg1024
1004
tokens/s
61.0
tokens/s
1.03
sec
pp1280+tg3072
985
tokens/s
48.3
tokens/s
1.32
sec
pp384+tg1152
1016
tokens/s
69.5
tokens/s
390
ms
pp64+tg1024
732
tokens/s
76.2
tokens/s
99
ms
pp16+tg1536
213
tokens/s
72.3
tokens/s
86
ms