TEST #3653 RESULTS
05/30/2026 - 7:15 AM
ACCELERATOR
MODEL
185
tokens/s
generation
1.59
sec
time to first token
7818
tokens/s
prompt
969
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14400F (alderlake)
RAM
15.4GB
OS
Linux
Kernel Release
7.0.0-22-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #22-Ubuntu SMP PREEMPT_DYNAMIC Mon May 25 15:54:34 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
9849
tokens/s
207
tokens/s
109
ms
pp4096+tg256
5726
tokens/s
122
tokens/s
724
ms
pp2048+tg256
7972
tokens/s
167
tokens/s
263
ms
pp2048+tg768
7854
tokens/s
160
tokens/s
267
ms
pp1024+tg1024
9973
tokens/s
188
tokens/s
107
ms
pp1280+tg3072
9153
tokens/s
149
tokens/s
145
ms
pp384+tg1152
12652
tokens/s
213
tokens/s
35
ms
pp64+tg1024
7181
tokens/s
235
tokens/s
13
ms
pp16+tg1536
1
tokens/s
223
tokens/s
12.63
sec