TEST #2999 RESULTS
03/07/2026 - 10:00 PM
ACCELERATOR
MODEL
231
tokens/s
generation
175
ms
time to first token
8209
tokens/s
prompt
2213
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699A v4 @ 2.40GHz (broadwell)
RAM
503.7GB
OS
Linux
Kernel Release
6.18.9-arch1-2.1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Wed, 11 Feb 2026 13:53:26 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
9962
tokens/s
244
tokens/s
107
ms
pp4096+tg256
6526
tokens/s
200
tokens/s
633
ms
pp2048+tg256
8567
tokens/s
227
tokens/s
244
ms
pp2048+tg768
8572
tokens/s
224
tokens/s
243
ms
pp1024+tg1024
10203
tokens/s
235
tokens/s
105
ms
pp1280+tg3072
9471
tokens/s
215
tokens/s
139
ms
pp384+tg1152
12659
tokens/s
241
tokens/s
34
ms
pp64+tg1024
7609
tokens/s
246
tokens/s
12
ms
pp16+tg1536
316
tokens/s
244
tokens/s
55
ms