TEST #2951 RESULTS
03/02/2026 - 12:18 PM
ACCELERATOR
MODEL
247
tokens/s
generation
80
ms
time to first token
17479
tokens/s
prompt
3780
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
23545
tokens/s
257
tokens/s
47
ms
pp4096+tg256
13866
tokens/s
228
tokens/s
300
ms
pp2048+tg256
19139
tokens/s
247
tokens/s
111
ms
pp2048+tg768
18862
tokens/s
242
tokens/s
113
ms
pp1024+tg1024
24678
tokens/s
254
tokens/s
46
ms
pp1280+tg3072
23262
tokens/s
241
tokens/s
59
ms
pp384+tg1152
24962
tokens/s
258
tokens/s
19
ms
pp64+tg1024
6656
tokens/s
259
tokens/s
14
ms
pp16+tg1536
2341
tokens/s
238
tokens/s
11
ms