TEST #2269 RESULTS
01/13/2026 - 2:05 AM
ACCELERATOR
MODEL
260
tokens/s
generation
146
ms
time to first token
9011
tokens/s
prompt
2521
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2133 CPU @ 3.60GHz (skylake-avx512)
RAM
94.3GB
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
11506
tokens/s
283
tokens/s
93
ms
pp4096+tg256
7878
tokens/s
197
tokens/s
525
ms
pp2048+tg256
10123
tokens/s
246
tokens/s
207
ms
pp2048+tg768
10123
tokens/s
238
tokens/s
207
ms
pp1024+tg1024
11600
tokens/s
264
tokens/s
92
ms
pp1280+tg3072
10952
tokens/s
227
tokens/s
121
ms
pp384+tg1152
11172
tokens/s
288
tokens/s
38
ms
pp64+tg1024
6940
tokens/s
304
tokens/s
12
ms
pp16+tg1536
804
tokens/s
294
tokens/s
23
ms