TEST #2911 RESULTS
02/26/2026 - 6:09 PM
ACCELERATOR
MODEL
99.1
tokens/s
generation
979
ms
time to first token
1272
tokens/s
prompt
505
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 4P+6E
RAM
16GB
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 20:54:05 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T8142
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1562
tokens/s
110
tokens/s
665
ms
pp4096+tg256
1233
tokens/s
71.9
tokens/s
3.34
sec
pp2048+tg256
1446
tokens/s
92.4
tokens/s
1.43
sec
pp2048+tg768
1432
tokens/s
89.2
tokens/s
1.44
sec
pp1024+tg1024
1518
tokens/s
101
tokens/s
684
ms
pp1280+tg3072
1511
tokens/s
84.4
tokens/s
857
ms
pp384+tg1152
1526
tokens/s
111
tokens/s
260
ms
pp64+tg1024
916
tokens/s
118
tokens/s
78
ms
pp16+tg1536
307
tokens/s
114
tokens/s
60
ms