TEST #1034 RESULTS
06/11/2025 - 9:52 PM
ACCELERATOR
MODEL
126
tokens/s
generation
572
ms
time to first token
1971
tokens/s
prompt
757
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
32GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:33:47 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2629
tokens/s
140
tokens/s
397
ms
pp4096+tg256
2386
tokens/s
88.0
tokens/s
1.73
sec
pp2048+tg256
2507
tokens/s
116
tokens/s
825
ms
pp2048+tg768
2443
tokens/s
112
tokens/s
847
ms
pp1024+tg1024
2472
tokens/s
129
tokens/s
421
ms
pp1280+tg3072
2383
tokens/s
105
tokens/s
545
ms
pp384+tg1152
2097
tokens/s
143
tokens/s
189
ms
pp64+tg1024
629
tokens/s
154
tokens/s
108
ms
pp16+tg1536
191
tokens/s
147
tokens/s
91
ms