TEST #1422 RESULTS
08/24/2025 - 1:14 PM
ACCELERATOR
MODEL
40.4
tokens/s
generation
434
ms
time to first token
3211
tokens/s
prompt
669
LocalScore
HOW YOU STACK UP
Explore All ResultsGranite 3.3 8b Instruct - 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
4009
tokens/s
40.1
tokens/s
281
ms
pp4096+tg256
2693
tokens/s
38.7
tokens/s
1.55
sec
pp2048+tg256
3461
tokens/s
40.6
tokens/s
616
ms
pp2048+tg768
3488
tokens/s
39.5
tokens/s
612
ms
pp1024+tg1024
4012
tokens/s
40.4
tokens/s
281
ms
pp1280+tg3072
3896
tokens/s
39.3
tokens/s
353
ms
pp384+tg1152
4796
tokens/s
41.0
tokens/s
104
ms
pp64+tg1024
1967
tokens/s
42.0
tokens/s
57
ms
pp16+tg1536
576
tokens/s
41.8
tokens/s
50
ms