TEST #2603 RESULTS
02/12/2026 - 7:09 AM
ACCELERATOR
MODEL
110
tokens/s
generation
627
ms
time to first token
1845
tokens/s
prompt
687
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
64GB
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 21:09:40 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2421
tokens/s
123
tokens/s
431
ms
pp4096+tg256
2180
tokens/s
81.5
tokens/s
1.89
sec
pp2048+tg256
1937
tokens/s
93.9
tokens/s
1.08
sec
pp2048+tg768
2371
tokens/s
105
tokens/s
872
ms
pp1024+tg1024
2369
tokens/s
119
tokens/s
439
ms
pp1280+tg3072
2315
tokens/s
97.0
tokens/s
561
ms
pp384+tg1152
2039
tokens/s
123
tokens/s
195
ms
pp64+tg1024
781
tokens/s
131
tokens/s
89
ms
pp16+tg1536
194
tokens/s
122
tokens/s
89
ms