TEST #1238 RESULTS
07/23/2025 - 9:00 AM
ACCELERATOR
MODEL
220
tokens/s
generation
144
ms
time to first token
9950
tokens/s
prompt
2480
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699 v3 @ 2.30GHz (haswell)
RAM
62.8GB
OS
Linux
Kernel Release
6.15.7-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu, 17 Jul 2025 21:05:29 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12537
tokens/s
230
tokens/s
86
ms
pp4096+tg256
7611
tokens/s
190
tokens/s
544
ms
pp2048+tg256
10268
tokens/s
216
tokens/s
204
ms
pp2048+tg768
10258
tokens/s
212
tokens/s
204
ms
pp1024+tg1024
12431
tokens/s
224
tokens/s
87
ms
pp1280+tg3072
11597
tokens/s
207
tokens/s
115
ms
pp384+tg1152
15074
tokens/s
232
tokens/s
30
ms
pp64+tg1024
7247
tokens/s
239
tokens/s
13
ms
pp16+tg1536
2531
tokens/s
232
tokens/s
11
ms