TEST #3423 RESULTS
05/01/2026 - 10:38 PM
ACCELERATOR
MODEL
253
tokens/s
generation
143
ms
time to first token
9138
tokens/s
prompt
2526
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2673 v4 @ 2.30GHz (broadwell)
RAM
125.8GB
OS
Linux
Kernel Release
6.17.0-23-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #23~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 14 16:11:48 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11832
tokens/s
273
tokens/s
90
ms
pp4096+tg256
8042
tokens/s
194
tokens/s
515
ms
pp2048+tg256
10415
tokens/s
239
tokens/s
201
ms
pp2048+tg768
10357
tokens/s
232
tokens/s
202
ms
pp1024+tg1024
11846
tokens/s
257
tokens/s
90
ms
pp1280+tg3072
11045
tokens/s
221
tokens/s
120
ms
pp384+tg1152
12276
tokens/s
278
tokens/s
35
ms
pp64+tg1024
5534
tokens/s
295
tokens/s
16
ms
pp16+tg1536
896
tokens/s
286
tokens/s
21
ms