TEST #1210 RESULTS
07/11/2025 - 8:37 PM
ACCELERATOR
MODEL
32.0
tokens/s
generation
6.95
sec
time to first token
216
tokens/s
prompt
100
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
290
tokens/s
34.6
tokens/s
3.56
sec
pp4096+tg256
179
tokens/s
27.1
tokens/s
22.93
sec
pp2048+tg256
164
tokens/s
31.2
tokens/s
12.55
sec
pp2048+tg768
191
tokens/s
30.2
tokens/s
10.75
sec
pp1024+tg1024
177
tokens/s
31.5
tokens/s
5.81
sec
pp1280+tg3072
280
tokens/s
29.4
tokens/s
4.59
sec
pp384+tg1152
195
tokens/s
34.0
tokens/s
2.00
sec
pp64+tg1024
312
tokens/s
35.8
tokens/s
232
ms
pp16+tg1536
153
tokens/s
34.3
tokens/s
131
ms