TEST #2899 RESULTS
02/25/2026 - 6:53 PM
ACCELERATOR
MODEL
167
tokens/s
generation
360
ms
time to first token
3325
tokens/s
prompt
1156
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
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
4203
tokens/s
184
tokens/s
249
ms
pp4096+tg256
3512
tokens/s
118
tokens/s
1.17
sec
pp2048+tg256
3941
tokens/s
153
tokens/s
526
ms
pp2048+tg768
3909
tokens/s
148
tokens/s
530
ms
pp1024+tg1024
4023
tokens/s
171
tokens/s
260
ms
pp1280+tg3072
4127
tokens/s
140
tokens/s
316
ms
pp384+tg1152
3581
tokens/s
190
tokens/s
112
ms
pp64+tg1024
2189
tokens/s
205
tokens/s
34
ms
pp16+tg1536
438
tokens/s
196
tokens/s
41
ms