TEST #1511 RESULTS
09/11/2025 - 10:28 PM
ACCELERATOR
MODEL
307
tokens/s
generation
111
ms
time to first token
12325
tokens/s
prompt
3241
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper PRO 3945WX 12-Cores (znver2)
RAM
125.6GB
OS
Linux
Kernel Release
6.12.46-1-lts
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue, 09 Sep 2025 18:30:25 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
15339
tokens/s
314
tokens/s
70
ms
pp4096+tg256
10204
tokens/s
261
tokens/s
405
ms
pp2048+tg256
13168
tokens/s
299
tokens/s
159
ms
pp2048+tg768
13184
tokens/s
294
tokens/s
159
ms
pp1024+tg1024
15559
tokens/s
314
tokens/s
69
ms
pp1280+tg3072
14409
tokens/s
288
tokens/s
92
ms
pp384+tg1152
17158
tokens/s
327
tokens/s
25
ms
pp64+tg1024
10195
tokens/s
337
tokens/s
9
ms
pp16+tg1536
1707
tokens/s
332
tokens/s
12
ms