TEST #2958 RESULTS
03/03/2026 - 3:20 AM
ACCELERATOR
MODEL
235
tokens/s
generation
113
ms
time to first token
11682
tokens/s
prompt
2894
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper PRO 5945WX 12-Cores (znver3)
RAM
127.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
15471
tokens/s
241
tokens/s
70
ms
pp4096+tg256
10257
tokens/s
214
tokens/s
404
ms
pp2048+tg256
13202
tokens/s
231
tokens/s
160
ms
pp2048+tg768
13233
tokens/s
232
tokens/s
159
ms
pp1024+tg1024
15381
tokens/s
239
tokens/s
71
ms
pp1280+tg3072
14468
tokens/s
203
tokens/s
93
ms
pp384+tg1152
14351
tokens/s
250
tokens/s
31
ms
pp64+tg1024
7570
tokens/s
251
tokens/s
12
ms
pp16+tg1536
1203
tokens/s
251
tokens/s
17
ms