TEST #1136 RESULTS
06/27/2025 - 9:45 AM
ACCELERATOR
MODEL
331
tokens/s
generation
96
ms
time to first token
13990
tokens/s
prompt
3638
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2235 CPU @ 3.80GHz (cascadelake)
RAM
188.3GB
OS
Linux
Kernel Release
6.1.0-37-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.1.140-1 (2025-05-22)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
16366
tokens/s
353
tokens/s
66
ms
pp4096+tg256
12001
tokens/s
282
tokens/s
346
ms
pp2048+tg256
15534
tokens/s
323
tokens/s
135
ms
pp2048+tg768
15652
tokens/s
318
tokens/s
135
ms
pp1024+tg1024
17640
tokens/s
337
tokens/s
61
ms
pp1280+tg3072
16762
tokens/s
309
tokens/s
79
ms
pp384+tg1152
20147
tokens/s
346
tokens/s
22
ms
pp64+tg1024
10138
tokens/s
355
tokens/s
9
ms
pp16+tg1536
1673
tokens/s
354
tokens/s
12
ms