TEST #3673 RESULTS
06/02/2026 - 11:28 PM
ACCELERATOR
MODEL
121
tokens/s
generation
572
ms
time to first token
2137
tokens/s
prompt
767
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
24GB
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 20:24:22 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2608
tokens/s
139
tokens/s
400
ms
pp4096+tg256
2152
tokens/s
78.9
tokens/s
1.92
sec
pp2048+tg256
2501
tokens/s
109
tokens/s
828
ms
pp2048+tg768
2493
tokens/s
104
tokens/s
831
ms
pp1024+tg1024
2600
tokens/s
124
tokens/s
402
ms
pp1280+tg3072
2517
tokens/s
97.5
tokens/s
517
ms
pp384+tg1152
2306
tokens/s
138
tokens/s
174
ms
pp64+tg1024
1539
tokens/s
151
tokens/s
47
ms
pp16+tg1536
518
tokens/s
144
tokens/s
36
ms