TEST #3616 RESULTS
05/26/2026 - 1:49 PM
ACCELERATOR
MODEL
330
tokens/s
generation
108
ms
time to first token
12190
tokens/s
prompt
3340
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
30.3GB
OS
Linux
Kernel Release
7.0.0-15-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #15-Ubuntu SMP PREEMPT_DYNAMIC Wed Apr 22 16:06:43 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
15643
tokens/s
349
tokens/s
68
ms
pp4096+tg256
10629
tokens/s
284
tokens/s
389
ms
pp2048+tg256
13858
tokens/s
326
tokens/s
151
ms
pp2048+tg768
13917
tokens/s
318
tokens/s
150
ms
pp1024+tg1024
16025
tokens/s
334
tokens/s
67
ms
pp1280+tg3072
15026
tokens/s
308
tokens/s
88
ms
pp384+tg1152
17400
tokens/s
345
tokens/s
25
ms
pp64+tg1024
6387
tokens/s
357
tokens/s
13
ms
pp16+tg1536
823
tokens/s
352
tokens/s
22
ms