TEST #76 RESULTS
03/28/2025 - 9:10 PM
ACCELERATOR
MODEL
237
tokens/s
generation
142
ms
time to first token
10703
tokens/s
prompt
2616
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7352 24-Core Processor (znver2)
RAM
251.6GB
OS
Linux
Kernel Release
6.8.0-40-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #40~22.04.3-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 30 17:30:19 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
13738
tokens/s
247
tokens/s
79
ms
pp4096+tg256
7363
tokens/s
209
tokens/s
561
ms
pp2048+tg256
10647
tokens/s
232
tokens/s
197
ms
pp2048+tg768
10613
tokens/s
229
tokens/s
197
ms
pp1024+tg1024
13736
tokens/s
240
tokens/s
79
ms
pp1280+tg3072
12817
tokens/s
224
tokens/s
104
ms
pp384+tg1152
18067
tokens/s
247
tokens/s
25
ms
pp64+tg1024
8449
tokens/s
253
tokens/s
11
ms
pp16+tg1536
897
tokens/s
250
tokens/s
22
ms