TEST #2932 RESULTS
02/27/2026 - 1:30 PM
ACCELERATOR
MODEL
117
tokens/s
generation
568
ms
time to first token
2119
tokens/s
prompt
759
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:34:05 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2677
tokens/s
133
tokens/s
390
ms
pp4096+tg256
2180
tokens/s
77.0
tokens/s
1.89
sec
pp2048+tg256
2488
tokens/s
106
tokens/s
833
ms
pp2048+tg768
2529
tokens/s
101
tokens/s
819
ms
pp1024+tg1024
2590
tokens/s
120
tokens/s
403
ms
pp1280+tg3072
2547
tokens/s
94.8
tokens/s
511
ms
pp384+tg1152
2425
tokens/s
136
tokens/s
165
ms
pp64+tg1024
1249
tokens/s
149
tokens/s
57
ms
pp16+tg1536
389
tokens/s
142
tokens/s
47
ms