TEST #972 RESULTS
06/02/2025 - 4:59 AM
ACCELERATOR
MODEL
359
tokens/s
generation
57
ms
time to first token
24549
tokens/s
prompt
5380
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 5218 CPU @ 2.30GHz (cascadelake)
RAM
503.7GB
OS
Linux
Kernel Release
6.8.0-58-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #60-Ubuntu SMP PREEMPT_DYNAMIC Fri Mar 14 18:29:48 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
32262
tokens/s
365
tokens/s
34
ms
pp4096+tg256
19464
tokens/s
332
tokens/s
214
ms
pp2048+tg256
27235
tokens/s
369
tokens/s
78
ms
pp2048+tg768
27179
tokens/s
350
tokens/s
78
ms
pp1024+tg1024
33850
tokens/s
363
tokens/s
33
ms
pp1280+tg3072
32360
tokens/s
356
tokens/s
42
ms
pp384+tg1152
34134
tokens/s
366
tokens/s
14
ms
pp64+tg1024
10833
tokens/s
363
tokens/s
9
ms
pp16+tg1536
3622
tokens/s
369
tokens/s
7
ms