TEST #2227 RESULTS
01/10/2026 - 6:54 PM
ACCELERATOR
MODEL
74.8
tokens/s
generation
393
ms
time to first token
3431
tokens/s
prompt
868
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
61.9GB
OS
Linux
Kernel Release
6.17.9-76061709-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202511241048~1764607909~24.04~df6b2b6 SMP PREEMPT_DYNAMIC Mon D
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4172
tokens/s
87.9
tokens/s
257
ms
pp4096+tg256
3008
tokens/s
47.1
tokens/s
1.38
sec
pp2048+tg256
3684
tokens/s
66.0
tokens/s
571
ms
pp2048+tg768
3689
tokens/s
62.9
tokens/s
570
ms
pp1024+tg1024
4117
tokens/s
75.6
tokens/s
261
ms
pp1280+tg3072
3915
tokens/s
58.4
tokens/s
339
ms
pp384+tg1152
4309
tokens/s
87.5
tokens/s
99
ms
pp64+tg1024
2856
tokens/s
96.8
tokens/s
31
ms
pp16+tg1536
1133
tokens/s
91.3
tokens/s
23
ms