TEST #2267 RESULTS
01/12/2026 - 10:58 PM
ACCELERATOR
MODEL
119
tokens/s
generation
564
ms
time to first token
2115
tokens/s
prompt
765
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
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2695
tokens/s
142
tokens/s
387
ms
pp4096+tg256
2220
tokens/s
78.9
tokens/s
1.86
sec
pp2048+tg256
2549
tokens/s
107
tokens/s
813
ms
pp2048+tg768
2485
tokens/s
102
tokens/s
834
ms
pp1024+tg1024
2596
tokens/s
121
tokens/s
402
ms
pp1280+tg3072
2566
tokens/s
95.4
tokens/s
507
ms
pp384+tg1152
2395
tokens/s
137
tokens/s
167
ms
pp64+tg1024
1167
tokens/s
150
tokens/s
61
ms
pp16+tg1536
361
tokens/s
143
tokens/s
50
ms