TEST #2248 RESULTS
01/12/2026 - 11:37 AM
ACCELERATOR
MODEL
260
tokens/s
generation
160
ms
time to first token
8801
tokens/s
prompt
2430
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
QEMU Virtual CPU version 2.5+
RAM
7.8GB
OS
Linux
Kernel Release
6.8.0-90-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #91-Ubuntu SMP PREEMPT_DYNAMIC Tue Nov 18 14:14:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10847
tokens/s
275
tokens/s
98
ms
pp4096+tg256
6907
tokens/s
223
tokens/s
598
ms
pp2048+tg256
9201
tokens/s
254
tokens/s
227
ms
pp2048+tg768
9212
tokens/s
249
tokens/s
226
ms
pp1024+tg1024
11032
tokens/s
265
tokens/s
97
ms
pp1280+tg3072
10229
tokens/s
243
tokens/s
129
ms
pp384+tg1152
12302
tokens/s
274
tokens/s
35
ms
pp64+tg1024
8220
tokens/s
282
tokens/s
11
ms
pp16+tg1536
1256
tokens/s
278
tokens/s
16
ms