TEST #132 RESULTS
03/28/2025 - 10:14 PM
ACCELERATOR
MODEL
315
tokens/s
generation
107
ms
time to first token
12562
tokens/s
prompt
3329
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.5.0-44-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #44~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jun 18 14:36:16 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
16142
tokens/s
343
tokens/s
66
ms
pp4096+tg256
10610
tokens/s
277
tokens/s
390
ms
pp2048+tg256
13745
tokens/s
317
tokens/s
152
ms
pp2048+tg768
13692
tokens/s
310
tokens/s
153
ms
pp1024+tg1024
16051
tokens/s
326
tokens/s
67
ms
pp1280+tg3072
14777
tokens/s
285
tokens/s
90
ms
pp384+tg1152
17013
tokens/s
319
tokens/s
25
ms
pp64+tg1024
9562
tokens/s
333
tokens/s
9
ms
pp16+tg1536
1470
tokens/s
326
tokens/s
14
ms