TEST #69 RESULTS
03/28/2025 - 9:01 PM
ACCELERATOR
MODEL
335
tokens/s
generation
68
ms
time to first token
18590
tokens/s
prompt
4512
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Platinum 8352Y CPU @ 2.20GHz (icelake-server)
RAM
2015.5GB
OS
Linux
Kernel Release
6.5.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue May 7 09:00:52 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
25522
tokens/s
336
tokens/s
43
ms
pp4096+tg256
18160
tokens/s
315
tokens/s
229
ms
pp2048+tg256
23175
tokens/s
329
tokens/s
91
ms
pp2048+tg768
20604
tokens/s
326
tokens/s
102
ms
pp1024+tg1024
24401
tokens/s
339
tokens/s
45
ms
pp1280+tg3072
22959
tokens/s
324
tokens/s
59
ms
pp384+tg1152
22909
tokens/s
346
tokens/s
20
ms
pp64+tg1024
7144
tokens/s
352
tokens/s
12
ms
pp16+tg1536
2439
tokens/s
351
tokens/s
10
ms