TEST #759 RESULTS
04/23/2025 - 3:16 AM
ACCELERATOR
MODEL
263
tokens/s
generation
161
ms
time to first token
8943
tokens/s
prompt
2445
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 185H (alderlake)
RAM
93.8GB
OS
Linux
Kernel Release
6.14.3-2-cachyos
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun, 20 Apr 2025 20:28:57 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11284
tokens/s
278
tokens/s
94
ms
pp4096+tg256
7058
tokens/s
224
tokens/s
585
ms
pp2048+tg256
9359
tokens/s
256
tokens/s
223
ms
pp2048+tg768
9364
tokens/s
252
tokens/s
223
ms
pp1024+tg1024
11241
tokens/s
267
tokens/s
95
ms
pp1280+tg3072
10569
tokens/s
245
tokens/s
125
ms
pp384+tg1152
12689
tokens/s
277
tokens/s
34
ms
pp64+tg1024
8628
tokens/s
284
tokens/s
11
ms
pp16+tg1536
295
tokens/s
282
tokens/s
58
ms