TEST #3164 RESULTS
03/23/2026 - 4:19 PM
ACCELERATOR
MODEL
118
tokens/s
generation
435
ms
time to first token
2965
tokens/s
prompt
929
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2135 CPU @ 3.70GHz (skylake-avx512)
RAM
125.4GB
OS
Linux
Kernel Release
6.17.13-2-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.17.13-2 (2026-03-13T08:06Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3653
tokens/s
111
tokens/s
289
ms
pp4096+tg256
2719
tokens/s
77.1
tokens/s
1.52
sec
pp2048+tg256
3285
tokens/s
107
tokens/s
633
ms
pp2048+tg768
3284
tokens/s
104
tokens/s
633
ms
pp1024+tg1024
3654
tokens/s
124
tokens/s
288
ms
pp1280+tg3072
3399
tokens/s
97.7
tokens/s
384
ms
pp384+tg1152
3780
tokens/s
140
tokens/s
108
ms
pp64+tg1024
2100
tokens/s
152
tokens/s
36
ms
pp16+tg1536
813
tokens/s
145
tokens/s
25
ms