TEST #2811 RESULTS
02/23/2026 - 10:57 PM
ACCELERATOR
MODEL
123
tokens/s
generation
555
ms
time to first token
2242
tokens/s
prompt
793
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
64GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:48:41 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2698
tokens/s
141
tokens/s
387
ms
pp4096+tg256
2209
tokens/s
79.2
tokens/s
1.87
sec
pp2048+tg256
2545
tokens/s
111
tokens/s
813
ms
pp2048+tg768
2535
tokens/s
106
tokens/s
817
ms
pp1024+tg1024
2670
tokens/s
126
tokens/s
391
ms
pp1280+tg3072
2648
tokens/s
98.6
tokens/s
491
ms
pp384+tg1152
2597
tokens/s
143
tokens/s
154
ms
pp64+tg1024
1690
tokens/s
157
tokens/s
44
ms
pp16+tg1536
583
tokens/s
150
tokens/s
33
ms