TEST #122 RESULTS
03/28/2025 - 10:03 PM
ACCELERATOR
MODEL
297
tokens/s
generation
137
ms
time to first token
10074
tokens/s
prompt
2795
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5500 (znver3)
RAM
86.3GB
OS
Linux
Kernel Release
5.15.0-126-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #136~20.04.1-Ubuntu SMP Thu Nov 14 16:38:05 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12208
tokens/s
317
tokens/s
87
ms
pp4096+tg256
8251
tokens/s
251
tokens/s
501
ms
pp2048+tg256
10573
tokens/s
290
tokens/s
197
ms
pp2048+tg768
10591
tokens/s
283
tokens/s
197
ms
pp1024+tg1024
12456
tokens/s
302
tokens/s
85
ms
pp1280+tg3072
11714
tokens/s
274
tokens/s
113
ms
pp384+tg1152
14736
tokens/s
314
tokens/s
29
ms
pp64+tg1024
8874
tokens/s
325
tokens/s
10
ms
pp16+tg1536
1265
tokens/s
320
tokens/s
16
ms