TEST #1682 RESULTS
10/18/2025 - 8:23 PM
ACCELERATOR
MODEL
23.1
tokens/s
generation
5.59
sec
time to first token
223
tokens/s
prompt
97
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepSeek R1 0528 Qwen3 8B - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 6P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:30 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
250
tokens/s
25.2
tokens/s
4.13
sec
pp4096+tg256
231
tokens/s
18.0
tokens/s
17.78
sec
pp2048+tg256
245
tokens/s
22.0
tokens/s
8.42
sec
pp2048+tg768
244
tokens/s
21.4
tokens/s
8.43
sec
pp1024+tg1024
249
tokens/s
23.6
tokens/s
4.15
sec
pp1280+tg3072
248
tokens/s
20.5
tokens/s
5.21
sec
pp384+tg1152
249
tokens/s
25.2
tokens/s
1.58
sec
pp64+tg1024
205
tokens/s
26.4
tokens/s
348
ms
pp16+tg1536
86
tokens/s
25.7
tokens/s
221
ms