TEST #514 RESULTS
04/07/2025 - 7:08 PM
ACCELERATOR
MODEL
144
tokens/s
generation
330
ms
time to first token
4363
tokens/s
prompt
1241
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12700 (alderlake)
RAM
62.5GB
OS
Linux
Kernel Release
6.8.0-56-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #58-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 14 15:33:28 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
5079
tokens/s
159
tokens/s
208
ms
pp4096+tg256
3434
tokens/s
118
tokens/s
1.20
sec
pp2048+tg256
4291
tokens/s
140
tokens/s
484
ms
pp2048+tg768
4295
tokens/s
136
tokens/s
483
ms
pp1024+tg1024
5136
tokens/s
148
tokens/s
207
ms
pp1280+tg3072
4743
tokens/s
131
tokens/s
276
ms
pp384+tg1152
6005
tokens/s
155
tokens/s
70
ms
pp64+tg1024
5131
tokens/s
160
tokens/s
17
ms
pp16+tg1536
1151
tokens/s
153
tokens/s
19
ms