TEST #364 RESULTS
04/06/2025 - 12:52 PM
ACCELERATOR
MODEL
124
tokens/s
generation
552
ms
time to first token
2060
tokens/s
prompt
774
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
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:16 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2560
tokens/s
138
tokens/s
407
ms
pp4096+tg256
2406
tokens/s
87.3
tokens/s
1.71
sec
pp2048+tg256
2601
tokens/s
114
tokens/s
796
ms
pp2048+tg768
2626
tokens/s
110
tokens/s
789
ms
pp1024+tg1024
2580
tokens/s
127
tokens/s
404
ms
pp1280+tg3072
2570
tokens/s
104
tokens/s
506
ms
pp384+tg1152
2221
tokens/s
141
tokens/s
179
ms
pp64+tg1024
781
tokens/s
152
tokens/s
88
ms
pp16+tg1536
195
tokens/s
146
tokens/s
88
ms