TEST #2443 RESULTS
02/01/2026 - 5:47 AM
ACCELERATOR
MODEL
164
tokens/s
generation
375
ms
time to first token
3224
tokens/s
prompt
1122
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: Thu Jan 22 21:54:32 PST 2026; root:xnu-12377.80.0.501.1~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4032
tokens/s
185
tokens/s
259
ms
pp4096+tg256
3290
tokens/s
115
tokens/s
1.25
sec
pp2048+tg256
3833
tokens/s
150
tokens/s
541
ms
pp2048+tg768
3832
tokens/s
145
tokens/s
541
ms
pp1024+tg1024
3961
tokens/s
167
tokens/s
264
ms
pp1280+tg3072
3938
tokens/s
137
tokens/s
331
ms
pp384+tg1152
3594
tokens/s
184
tokens/s
112
ms
pp64+tg1024
1932
tokens/s
200
tokens/s
38
ms
pp16+tg1536
601
tokens/s
193
tokens/s
31
ms