TEST #2298 RESULTS
01/15/2026 - 1:48 PM
ACCELERATOR
MODEL
97.9
tokens/s
generation
165
ms
time to first token
8630
tokens/s
prompt
1724
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 3600 6-Core Processor (znver2)
RAM
7.7GB
OS
Linux
Kernel Release
6.6.87.2-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11502
tokens/s
128
tokens/s
98
ms
pp4096+tg256
7285
tokens/s
86.0
tokens/s
570
ms
pp2048+tg256
9120
tokens/s
125
tokens/s
232
ms
pp2048+tg768
9080
tokens/s
67.0
tokens/s
276
ms
pp1024+tg1024
11762
tokens/s
102
tokens/s
95
ms
pp1280+tg3072
10148
tokens/s
61.7
tokens/s
134
ms
pp384+tg1152
13436
tokens/s
105
tokens/s
35
ms
pp64+tg1024
4083
tokens/s
125
tokens/s
23
ms
pp16+tg1536
1253
tokens/s
79.9
tokens/s
20
ms