TEST #3676 RESULTS
06/03/2026 - 1:14 PM
ACCELERATOR
MODEL
41.9
tokens/s
generation
7.16
sec
time to first token
207
tokens/s
prompt
107
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i5-12400 (alderlake)
RAM
31GB
OS
Linux
Kernel Release
7.0.3-arch1-2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri, 01 May 2026 15:49:22 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
215
tokens/s
44.4
tokens/s
4.80
sec
pp4096+tg256
163
tokens/s
36.0
tokens/s
25.15
sec
pp2048+tg256
190
tokens/s
41.0
tokens/s
10.78
sec
pp2048+tg768
194
tokens/s
40.0
tokens/s
10.56
sec
pp1024+tg1024
214
tokens/s
42.4
tokens/s
4.80
sec
pp1280+tg3072
203
tokens/s
38.8
tokens/s
6.33
sec
pp384+tg1152
233
tokens/s
44.1
tokens/s
1.67
sec
pp64+tg1024
237
tokens/s
45.3
tokens/s
291
ms
pp16+tg1536
217
tokens/s
44.8
tokens/s
95
ms