TEST #2665 RESULTS
02/15/2026 - 5:34 PM
ACCELERATOR
MODEL
128
tokens/s
generation
539
ms
time to first token
2122
tokens/s
prompt
796
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
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:29 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2656
tokens/s
143
tokens/s
393
ms
pp4096+tg256
2441
tokens/s
88.9
tokens/s
1.69
sec
pp2048+tg256
2653
tokens/s
117
tokens/s
780
ms
pp2048+tg768
2631
tokens/s
113
tokens/s
787
ms
pp1024+tg1024
2655
tokens/s
130
tokens/s
393
ms
pp1280+tg3072
2645
tokens/s
107
tokens/s
491
ms
pp384+tg1152
2271
tokens/s
145
tokens/s
175
ms
pp64+tg1024
893
tokens/s
157
tokens/s
77
ms
pp16+tg1536
252
tokens/s
151
tokens/s
69
ms