TEST #776 RESULTS
04/26/2025 - 11:07 PM
ACCELERATOR
MODEL
181
tokens/s
generation
302
ms
time to first token
3925
tokens/s
prompt
1330
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
64GB
OS
Darwin
Kernel Release
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:22 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4945
tokens/s
202
tokens/s
212
ms
pp4096+tg256
4210
tokens/s
124
tokens/s
981
ms
pp2048+tg256
4718
tokens/s
164
tokens/s
440
ms
pp2048+tg768
4743
tokens/s
157
tokens/s
438
ms
pp1024+tg1024
4873
tokens/s
183
tokens/s
215
ms
pp1280+tg3072
4782
tokens/s
148
tokens/s
273
ms
pp384+tg1152
4467
tokens/s
208
tokens/s
90
ms
pp64+tg1024
2003
tokens/s
226
tokens/s
36
ms
pp16+tg1536
581
tokens/s
214
tokens/s
31
ms