TEST #1209 RESULTS
07/11/2025 - 8:26 PM
ACCELERATOR
MODEL
102
tokens/s
generation
327
ms
time to first token
4609
tokens/s
prompt
1128
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2150B CPU @ 3.00GHz (skylake-avx512)
RAM
125.4GB
OS
Linux
Kernel Release
6.8.12-11-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.8.12-11 (2025-05-22T09:39Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6113
tokens/s
126
tokens/s
176
ms
pp4096+tg256
3182
tokens/s
23.7
tokens/s
1.33
sec
pp2048+tg256
4638
tokens/s
91.0
tokens/s
452
ms
pp2048+tg768
4553
tokens/s
85.5
tokens/s
461
ms
pp1024+tg1024
5954
tokens/s
108
tokens/s
180
ms
pp1280+tg3072
5618
tokens/s
65.3
tokens/s
237
ms
pp384+tg1152
6710
tokens/s
130
tokens/s
64
ms
pp64+tg1024
3181
tokens/s
149
tokens/s
26
ms
pp16+tg1536
1530
tokens/s
138
tokens/s
16
ms