TEST #2302 RESULTS
01/15/2026 - 2:28 PM
ACCELERATOR
MODEL
258
tokens/s
generation
160
ms
time to first token
8807
tokens/s
prompt
2421
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11700K @ 3.60GHz (rocketlake)
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
10913
tokens/s
271
tokens/s
98
ms
pp4096+tg256
6861
tokens/s
221
tokens/s
602
ms
pp2048+tg256
9142
tokens/s
253
tokens/s
228
ms
pp2048+tg768
9123
tokens/s
248
tokens/s
229
ms
pp1024+tg1024
10952
tokens/s
264
tokens/s
97
ms
pp1280+tg3072
10319
tokens/s
241
tokens/s
128
ms
pp384+tg1152
12347
tokens/s
272
tokens/s
35
ms
pp64+tg1024
8233
tokens/s
279
tokens/s
11
ms
pp16+tg1536
1375
tokens/s
275
tokens/s
15
ms