TEST #953 RESULTS
05/29/2025 - 9:07 PM
ACCELERATOR
MODEL
285
tokens/s
generation
113
ms
time to first token
12204
tokens/s
prompt
3136
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6338N CPU @ 2.20GHz (icelake-server)
RAM
503.4GB
OS
Linux
Kernel Release
5.15.0-139-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #149~20.04.1-Ubuntu SMP Wed Apr 16 08:29:56 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
15819
tokens/s
295
tokens/s
68
ms
pp4096+tg256
9873
tokens/s
246
tokens/s
419
ms
pp2048+tg256
13290
tokens/s
279
tokens/s
158
ms
pp2048+tg768
13273
tokens/s
275
tokens/s
158
ms
pp1024+tg1024
15875
tokens/s
288
tokens/s
68
ms
pp1280+tg3072
14744
tokens/s
267
tokens/s
90
ms
pp384+tg1152
16848
tokens/s
297
tokens/s
26
ms
pp64+tg1024
8876
tokens/s
310
tokens/s
10
ms
pp16+tg1536
1236
tokens/s
305
tokens/s
16
ms