TEST #1726 RESULTS
11/03/2025 - 12:13 PM
ACCELERATOR
MODEL
17.4
tokens/s
generation
31.70
sec
time to first token
43
tokens/s
prompt
29
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2470 v2 @ 2.40GHz (ivybridge)
RAM
94.2GB
OS
Linux
Kernel Release
6.8.12-15-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.8.12-15 (2025-09-12T11:02Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
34
tokens/s
16.4
tokens/s
30.53
sec
pp4096+tg256
40
tokens/s
11.9
tokens/s
102.98
sec
pp2048+tg256
40
tokens/s
21.1
tokens/s
50.80
sec
pp2048+tg768
50
tokens/s
15.8
tokens/s
41.13
sec
pp1024+tg1024
48
tokens/s
17.5
tokens/s
21.55
sec
pp1280+tg3072
53
tokens/s
15.3
tokens/s
24.08
sec
pp384+tg1152
31
tokens/s
19.0
tokens/s
12.47
sec
pp64+tg1024
48
tokens/s
20.8
tokens/s
1.36
sec
pp16+tg1536
47
tokens/s
18.5
tokens/s
378
ms