TEST #1279 RESULTS
07/31/2025 - 3:13 PM
ACCELERATOR
MODEL
213
tokens/s
generation
194
ms
time to first token
7200
tokens/s
prompt
1991
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600G with Radeon Graphics (znver3)
RAM
46.9GB
OS
Linux
Kernel Release
6.11.0-29-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #29~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Jun 26 14:16:59 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8798
tokens/s
230
tokens/s
121
ms
pp4096+tg256
5765
tokens/s
180
tokens/s
716
ms
pp2048+tg256
7511
tokens/s
207
tokens/s
277
ms
pp2048+tg768
7514
tokens/s
203
tokens/s
277
ms
pp1024+tg1024
8767
tokens/s
213
tokens/s
121
ms
pp1280+tg3072
8307
tokens/s
193
tokens/s
159
ms
pp384+tg1152
10260
tokens/s
226
tokens/s
42
ms
pp64+tg1024
6682
tokens/s
233
tokens/s
14
ms
pp16+tg1536
1193
tokens/s
227
tokens/s
17
ms