TEST #3578 RESULTS
05/20/2026 - 11:29 AM
ACCELERATOR
MODEL
278
tokens/s
generation
126
ms
time to first token
9858
tokens/s
prompt
2791
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2690 v4 @ 2.60GHz (broadwell)
RAM
125.7GB
OS
Linux
Kernel Release
7.0.9-202.fc44.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon May 18 22:33:24 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11585
tokens/s
297
tokens/s
92
ms
pp4096+tg256
9505
tokens/s
217
tokens/s
436
ms
pp2048+tg256
11932
tokens/s
263
tokens/s
175
ms
pp2048+tg768
11886
tokens/s
256
tokens/s
176
ms
pp1024+tg1024
13471
tokens/s
288
tokens/s
79
ms
pp1280+tg3072
12461
tokens/s
247
tokens/s
106
ms
pp384+tg1152
12941
tokens/s
305
tokens/s
33
ms
pp64+tg1024
3916
tokens/s
320
tokens/s
19
ms
pp16+tg1536
1023
tokens/s
311
tokens/s
19
ms