TEST #3586 RESULTS
05/21/2026 - 11:17 AM
ACCELERATOR
MODEL
309
tokens/s
generation
133
ms
time to first token
11156
tokens/s
prompt
2957
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-14700KF (alderlake)
RAM
61.6GB
OS
Linux
Kernel Release
7.0.0-15-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #15-Ubuntu SMP PREEMPT_DYNAMIC Wed Apr 22 16:06:43 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
13633
tokens/s
322
tokens/s
78
ms
pp4096+tg256
8012
tokens/s
253
tokens/s
515
ms
pp2048+tg256
10952
tokens/s
293
tokens/s
190
ms
pp2048+tg768
10941
tokens/s
290
tokens/s
191
ms
pp1024+tg1024
13461
tokens/s
314
tokens/s
79
ms
pp1280+tg3072
12653
tokens/s
287
tokens/s
104
ms
pp384+tg1152
17918
tokens/s
336
tokens/s
24
ms
pp64+tg1024
9433
tokens/s
348
tokens/s
10
ms
pp16+tg1536
3401
tokens/s
338
tokens/s
8
ms