TEST #1229 RESULTS
07/19/2025 - 6:33 PM
ACCELERATOR
MODEL
102
tokens/s
generation
326
ms
time to first token
4607
tokens/s
prompt
1129
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
188.3GB
OS
Linux
Kernel Release
6.8.12-12-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.8.12-12 (2025-07-14T13:20Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6123
tokens/s
126
tokens/s
175
ms
pp4096+tg256
3201
tokens/s
23.7
tokens/s
1.32
sec
pp2048+tg256
4602
tokens/s
91.0
tokens/s
456
ms
pp2048+tg768
4624
tokens/s
85.5
tokens/s
454
ms
pp1024+tg1024
5948
tokens/s
108
tokens/s
180
ms
pp1280+tg3072
5583
tokens/s
65.3
tokens/s
238
ms
pp384+tg1152
6723
tokens/s
130
tokens/s
63
ms
pp64+tg1024
3234
tokens/s
149
tokens/s
25
ms
pp16+tg1536
1424
tokens/s
138
tokens/s
17
ms