TEST #1804 RESULTS
11/15/2025 - 10:05 PM
ACCELERATOR
MODEL
124
tokens/s
generation
559
ms
time to first token
2022
tokens/s
prompt
767
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
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:32:41 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2613
tokens/s
139
tokens/s
399
ms
pp4096+tg256
2392
tokens/s
88.1
tokens/s
1.72
sec
pp2048+tg256
2621
tokens/s
115
tokens/s
790
ms
pp2048+tg768
2467
tokens/s
110
tokens/s
839
ms
pp1024+tg1024
2565
tokens/s
127
tokens/s
407
ms
pp1280+tg3072
2609
tokens/s
104
tokens/s
498
ms
pp384+tg1152
1957
tokens/s
140
tokens/s
203
ms
pp64+tg1024
751
tokens/s
151
tokens/s
91
ms
pp16+tg1536
225
tokens/s
145
tokens/s
77
ms