TEST #3652 RESULTS
05/30/2026 - 6:47 AM
ACCELERATOR
MODEL
35.3
tokens/s
generation
5.43
sec
time to first token
278
tokens/s
prompt
122
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
295
tokens/s
38.4
tokens/s
3.50
sec
pp4096+tg256
218
tokens/s
28.8
tokens/s
18.81
sec
pp2048+tg256
265
tokens/s
35.0
tokens/s
7.76
sec
pp2048+tg768
238
tokens/s
32.5
tokens/s
8.64
sec
pp1024+tg1024
268
tokens/s
35.7
tokens/s
3.85
sec
pp1280+tg3072
272
tokens/s
31.5
tokens/s
4.74
sec
pp384+tg1152
317
tokens/s
38.7
tokens/s
1.24
sec
pp64+tg1024
337
tokens/s
38.4
tokens/s
215
ms
pp16+tg1536
297
tokens/s
38.6
tokens/s
77
ms