TEST #391 RESULTS
04/06/2025 - 3:50 PM
ACCELERATOR
MODEL
83.9
tokens/s
generation
455
ms
time to first token
2827
tokens/s
prompt
805
LocalScore
HOW YOU STACK UP
Explore All ResultsEuroLLM 9B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700T (alderlake)
RAM
125.5GB
OS
Linux
Kernel Release
6.1.0-32-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.1.129-1 (2025-03-06)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3182
tokens/s
87.3
tokens/s
335
ms
pp4096+tg256
2716
tokens/s
75.0
tokens/s
1.52
sec
pp2048+tg256
3181
tokens/s
84.5
tokens/s
656
ms
pp2048+tg768
3152
tokens/s
83.0
tokens/s
662
ms
pp1024+tg1024
3421
tokens/s
83.6
tokens/s
311
ms
pp1280+tg3072
3167
tokens/s
78.1
tokens/s
416
ms
pp384+tg1152
3281
tokens/s
85.3
tokens/s
129
ms
pp64+tg1024
2565
tokens/s
90.3
tokens/s
35
ms
pp16+tg1536
774
tokens/s
88.0
tokens/s
31
ms