TEST #442 RESULTS
04/06/2025 - 11:33 PM
ACCELERATOR
MODEL
214
tokens/s
generation
173
ms
time to first token
9161
tokens/s
prompt
2246
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 4600G with Radeon Graphics (znver2)
RAM
94.1GB
OS
Linux
Kernel Release
6.12.21-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.21-1 (2025-03-30)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11407
tokens/s
223
tokens/s
94
ms
pp4096+tg256
5817
tokens/s
189
tokens/s
710
ms
pp2048+tg256
8913
tokens/s
209
tokens/s
235
ms
pp2048+tg768
8801
tokens/s
206
tokens/s
238
ms
pp1024+tg1024
11380
tokens/s
217
tokens/s
96
ms
pp1280+tg3072
9800
tokens/s
202
tokens/s
135
ms
pp384+tg1152
15408
tokens/s
224
tokens/s
29
ms
pp64+tg1024
8322
tokens/s
231
tokens/s
12
ms
pp16+tg1536
2602
tokens/s
228
tokens/s
10
ms