TEST #1419 RESULTS
08/24/2025 - 12:39 PM
ACCELERATOR
MODEL
45.2
tokens/s
generation
368
ms
time to first token
3730
tokens/s
prompt
771
LocalScore
HOW YOU STACK UP
Explore All ResultsCogito v1 Preview Llama 8B - Q8_0
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.3GB
OS
Linux
Kernel Release
6.16.1-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri, 15 Aug 2025 16:04:43 +0000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4758
tokens/s
46.3
tokens/s
237
ms
pp4096+tg256
3223
tokens/s
43.4
tokens/s
1.29
sec
pp2048+tg256
4103
tokens/s
45.1
tokens/s
522
ms
pp2048+tg768
4101
tokens/s
45.0
tokens/s
523
ms
pp1024+tg1024
4773
tokens/s
45.8
tokens/s
237
ms
pp1280+tg3072
4653
tokens/s
44.3
tokens/s
296
ms
pp384+tg1152
5383
tokens/s
45.5
tokens/s
93
ms
pp64+tg1024
2111
tokens/s
45.8
tokens/s
51
ms
pp16+tg1536
464
tokens/s
45.5
tokens/s
56
ms