TEST #31 RESULTS
03/28/2025 - 5:22 PM
ACCELERATOR
MODEL
199
tokens/s
generation
73
ms
time to first token
17009
tokens/s
prompt
3593
LocalScore
HOW YOU STACK UP
Explore All ResultsGemma 3 1b It - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7352 24-Core Processor (znver2)
RAM
125.6GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
22334
tokens/s
205
tokens/s
51
ms
pp4096+tg256
19233
tokens/s
179
tokens/s
219
ms
pp2048+tg256
21086
tokens/s
203
tokens/s
102
ms
pp2048+tg768
21087
tokens/s
202
tokens/s
102
ms
pp1024+tg1024
22032
tokens/s
205
tokens/s
51
ms
pp1280+tg3072
20396
tokens/s
196
tokens/s
68
ms
pp384+tg1152
19716
tokens/s
199
tokens/s
25
ms
pp64+tg1024
6279
tokens/s
200
tokens/s
15
ms
pp16+tg1536
917
tokens/s
200
tokens/s
23
ms