TEST #1381 RESULTS
08/15/2025 - 3:43 AM
ACCELERATOR
MODEL
202
tokens/s
generation
207
ms
time to first token
7018
tokens/s
prompt
1900
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-11955M CPU @ 2.60GHz (tigerlake)
RAM
125.1GB
OS
Linux
Kernel Release
6.12.10-76061203-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202412060638~1753385872~22.04~dc2e00d SMP PREEMPT_DYNAMIC Thu J
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8429
tokens/s
216
tokens/s
127
ms
pp4096+tg256
5411
tokens/s
171
tokens/s
763
ms
pp2048+tg256
6695
tokens/s
194
tokens/s
311
ms
pp2048+tg768
7167
tokens/s
195
tokens/s
291
ms
pp1024+tg1024
8446
tokens/s
208
tokens/s
126
ms
pp1280+tg3072
7937
tokens/s
186
tokens/s
166
ms
pp384+tg1152
10358
tokens/s
213
tokens/s
41
ms
pp64+tg1024
7775
tokens/s
218
tokens/s
12
ms
pp16+tg1536
945
tokens/s
216
tokens/s
23
ms