TEST #1299 RESULTS
08/03/2025 - 3:43 PM
ACCELERATOR
MODEL
226
tokens/s
generation
145
ms
time to first token
9965
tokens/s
prompt
2494
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2680 v4 @ 2.40GHz (broadwell)
RAM
94.1GB
OS
Linux
Kernel Release
6.14.8-2-bpo12-pve
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC PMX 6.14.8-2~bpo12+1 (2025-07-22T13:15Z)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12352
tokens/s
236
tokens/s
87
ms
pp4096+tg256
7539
tokens/s
192
tokens/s
549
ms
pp2048+tg256
10169
tokens/s
221
tokens/s
206
ms
pp2048+tg768
10158
tokens/s
218
tokens/s
206
ms
pp1024+tg1024
12339
tokens/s
230
tokens/s
87
ms
pp1280+tg3072
11498
tokens/s
212
tokens/s
116
ms
pp384+tg1152
15100
tokens/s
238
tokens/s
30
ms
pp64+tg1024
7826
tokens/s
245
tokens/s
12
ms
pp16+tg1536
2703
tokens/s
239
tokens/s
10
ms