TEST #165 RESULTS
03/30/2025 - 8:04 PM
ACCELERATOR
MODEL
238
tokens/s
generation
1.49
sec
time to first token
16091
tokens/s
prompt
1371
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14600KF (alderlake)
RAM
62.6GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
21874
tokens/s
265
tokens/s
50
ms
pp4096+tg256
12068
tokens/s
155
tokens/s
346
ms
pp2048+tg256
17151
tokens/s
217
tokens/s
124
ms
pp2048+tg768
17171
tokens/s
204
tokens/s
124
ms
pp1024+tg1024
20907
tokens/s
243
tokens/s
53
ms
pp1280+tg3072
19157
tokens/s
191
tokens/s
71
ms
pp384+tg1152
25581
tokens/s
275
tokens/s
18
ms
pp64+tg1024
10908
tokens/s
302
tokens/s
9
ms
pp16+tg1536
1
tokens/s
288
tokens/s
12.58
sec