TEST #179 RESULTS
03/30/2025 - 8:25 PM
ACCELERATOR
MODEL
133
tokens/s
generation
483
ms
time to first token
2424
tokens/s
prompt
874
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 Distill Qwen 1.5B - 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
3054
tokens/s
143
tokens/s
342
ms
pp4096+tg256
2694
tokens/s
104
tokens/s
1.53
sec
pp2048+tg256
2904
tokens/s
127
tokens/s
713
ms
pp2048+tg768
2915
tokens/s
124
tokens/s
711
ms
pp1024+tg1024
2993
tokens/s
136
tokens/s
349
ms
pp1280+tg3072
3003
tokens/s
119
tokens/s
433
ms
pp384+tg1152
2572
tokens/s
146
tokens/s
156
ms
pp64+tg1024
1368
tokens/s
152
tokens/s
53
ms
pp16+tg1536
317
tokens/s
148
tokens/s
57
ms
