TEST #3325 RESULTS

04/16/2026 - 2:16 AM

9.9

tokens/s

generation

13.16

sec

time to first token

102

tokens/s

prompt

42

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M3 Pro 5P+6E
RAM
18GB
OS
Darwin
Kernel Release
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:33:36 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T6030
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
109
tokens/s
9.5
tokens/s
9.53
sec
pp4096+tg256
95
tokens/s
7.5
tokens/s
43.09
sec
pp2048+tg256
101
tokens/s
8.7
tokens/s
20.34
sec
pp2048+tg768
105
tokens/s
8.6
tokens/s
19.72
sec
pp1024+tg1024
109
tokens/s
9.1
tokens/s
9.54
sec
pp1280+tg3072
107
tokens/s
9.2
tokens/s
12.11
sec
pp384+tg1152
126
tokens/s
12.1
tokens/s
3.14
sec
pp64+tg1024
115
tokens/s
12.4
tokens/s
634
ms
pp16+tg1536
52
tokens/s
12.2
tokens/s
385
ms