TEST #2929 RESULTS
02/27/2026 - 1:17 PM
ACCELERATOR
MODEL
123
tokens/s
generation
575
ms
time to first token
1961
tokens/s
prompt
749
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
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:40 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2628
tokens/s
138
tokens/s
397
ms
pp4096+tg256
2379
tokens/s
87.0
tokens/s
1.73
sec
pp2048+tg256
2469
tokens/s
114
tokens/s
838
ms
pp2048+tg768
2437
tokens/s
110
tokens/s
849
ms
pp1024+tg1024
2316
tokens/s
125
tokens/s
449
ms
pp1280+tg3072
2641
tokens/s
104
tokens/s
492
ms
pp384+tg1152
1803
tokens/s
139
tokens/s
219
ms
pp64+tg1024
828
tokens/s
149
tokens/s
83
ms
pp16+tg1536
148
tokens/s
143
tokens/s
114
ms