TEST #131 RESULTS
03/28/2025 - 10:13 PM
ACCELERATOR
MODEL
332
tokens/s
generation
92
ms
time to first token
14470
tokens/s
prompt
3738
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
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
18125
tokens/s
342
tokens/s
59
ms
pp4096+tg256
12565
tokens/s
284
tokens/s
330
ms
pp2048+tg256
16266
tokens/s
325
tokens/s
129
ms
pp2048+tg768
16278
tokens/s
319
tokens/s
129
ms
pp1024+tg1024
18848
tokens/s
339
tokens/s
57
ms
pp1280+tg3072
17621
tokens/s
311
tokens/s
76
ms
pp384+tg1152
19583
tokens/s
349
tokens/s
22
ms
pp64+tg1024
9734
tokens/s
362
tokens/s
9
ms
pp16+tg1536
1210
tokens/s
356
tokens/s
16
ms