TEST #169 RESULTS
03/30/2025 - 8:08 PM
ACCELERATOR
MODEL
79.8
tokens/s
generation
315
ms
time to first token
4323
tokens/s
prompt
1031
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B 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
5371
tokens/s
88.6
tokens/s
202
ms
pp4096+tg256
3787
tokens/s
56.7
tokens/s
1.10
sec
pp2048+tg256
4708
tokens/s
74.1
tokens/s
448
ms
pp2048+tg768
4706
tokens/s
71.2
tokens/s
449
ms
pp1024+tg1024
5392
tokens/s
81.9
tokens/s
201
ms
pp1280+tg3072
5154
tokens/s
67.5
tokens/s
260
ms
pp384+tg1152
5930
tokens/s
90.0
tokens/s
75
ms
pp64+tg1024
3593
tokens/s
95.9
tokens/s
27
ms
pp16+tg1536
264
tokens/s
92.2
tokens/s
70
ms