TEST #183 RESULTS

03/30/2025 - 9:13 PM

51.9

tokens/s

generation

2.02

sec

time to first token

598

tokens/s

prompt

249

LocalScore

HOW YOU STACK UP
Explore All Results

DeepSeek R1 Distill Qwen 7B - Q4_K - Medium

SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
OS
Darwin
Kernel Release
24.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.1.0: Thu Nov 14 18:15:21 PST 2024; root:xnu-11215.41.3~13/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
711
tokens/s
56.7
tokens/s
1.46
sec
pp4096+tg256
663
tokens/s
43.5
tokens/s
6.20
sec
pp2048+tg256
699
tokens/s
51.9
tokens/s
2.95
sec
pp2048+tg768
694
tokens/s
50.4
tokens/s
2.97
sec
pp1024+tg1024
660
tokens/s
54.3
tokens/s
1.57
sec
pp1280+tg3072
593
tokens/s
48.3
tokens/s
2.18
sec
pp384+tg1152
701
tokens/s
55.2
tokens/s
564
ms
pp64+tg1024
500
tokens/s
55.1
tokens/s
144
ms
pp16+tg1536
160
tokens/s
52.1
tokens/s
116
ms