TEST #905 RESULTS
05/19/2025 - 1:29 AM
ACCELERATOR
MODEL
301
tokens/s
generation
105
ms
time to first token
12964
tokens/s
prompt
3342
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.8.0-59-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #61~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 15 17:03:15 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
16596
tokens/s
311
tokens/s
65
ms
pp4096+tg256
10867
tokens/s
249
tokens/s
381
ms
pp2048+tg256
14171
tokens/s
296
tokens/s
148
ms
pp2048+tg768
14146
tokens/s
288
tokens/s
148
ms
pp1024+tg1024
16571
tokens/s
307
tokens/s
65
ms
pp1280+tg3072
15650
tokens/s
277
tokens/s
85
ms
pp384+tg1152
17929
tokens/s
321
tokens/s
24
ms
pp64+tg1024
9456
tokens/s
334
tokens/s
10
ms
pp16+tg1536
1288
tokens/s
328
tokens/s
15
ms