TEST #3004 RESULTS
03/07/2026 - 10:03 PM
ACCELERATOR
MODEL
220
tokens/s
generation
122
ms
time to first token
12968
tokens/s
prompt
2862
LocalScore
HOW YOU STACK UP
Explore All ResultsOpenELM 270M Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
16527
tokens/s
207
tokens/s
67
ms
pp4096+tg256
8372
tokens/s
210
tokens/s
494
ms
pp2048+tg256
12520
tokens/s
224
tokens/s
170
ms
pp2048+tg768
12378
tokens/s
221
tokens/s
170
ms
pp1024+tg1024
17206
tokens/s
220
tokens/s
64
ms
pp1280+tg3072
15764
tokens/s
219
tokens/s
85
ms
pp384+tg1152
22074
tokens/s
223
tokens/s
23
ms
pp64+tg1024
9192
tokens/s
229
tokens/s
11
ms
pp16+tg1536
2681
tokens/s
224
tokens/s
10
ms