TEST #185 RESULTS
04/02/2025 - 5:27 PM
ACCELERATOR
MODEL
300
tokens/s
generation
100
ms
time to first token
13357
tokens/s
prompt
3428
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q6_K
SYSTEM
CPU
AMD EPYC 7352 24-Core Processor (znver2)
RAM
125.6GB
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
16554
tokens/s
302
tokens/s
65
ms
pp4096+tg256
11935
tokens/s
265
tokens/s
347
ms
pp2048+tg256
15181
tokens/s
267
tokens/s
138
ms
pp2048+tg768
14268
tokens/s
295
tokens/s
147
ms
pp1024+tg1024
17513
tokens/s
309
tokens/s
62
ms
pp1280+tg3072
16148
tokens/s
289
tokens/s
83
ms
pp384+tg1152
18457
tokens/s
319
tokens/s
24
ms
pp64+tg1024
9269
tokens/s
332
tokens/s
10
ms
pp16+tg1536
888
tokens/s
326
tokens/s
21
ms