TEST #1326 RESULTS
08/07/2025 - 7:23 AM
ACCELERATOR
MODEL
17.9
tokens/s
generation
3.96
sec
time to first token
336
tokens/s
prompt
115
LocalScore
HOW YOU STACK UP
Explore All ResultsMistral-7B-Instruct-v0.3 - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-6600K CPU @ 3.50GHz (skylake)
RAM
15.1GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:01:58 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
335
tokens/s
19.6
tokens/s
3.10
sec
pp4096+tg256
320
tokens/s
13.0
tokens/s
12.88
sec
pp2048+tg256
347
tokens/s
16.9
tokens/s
5.97
sec
pp2048+tg768
351
tokens/s
16.2
tokens/s
5.90
sec
pp1024+tg1024
372
tokens/s
18.2
tokens/s
2.80
sec
pp1280+tg3072
365
tokens/s
15.3
tokens/s
3.56
sec
pp384+tg1152
384
tokens/s
19.9
tokens/s
1.05
sec
pp64+tg1024
351
tokens/s
21.3
tokens/s
226
ms
pp16+tg1536
197
tokens/s
20.5
tokens/s
124
ms