TEST #2950 RESULTS
03/02/2026 - 11:31 AM
ACCELERATOR
MODEL
180
tokens/s
generation
309
ms
time to first token
3769
tokens/s
prompt
1300
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
128GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:48:41 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4935
tokens/s
204
tokens/s
212
ms
pp4096+tg256
4192
tokens/s
123
tokens/s
985
ms
pp2048+tg256
4647
tokens/s
164
tokens/s
447
ms
pp2048+tg768
4585
tokens/s
158
tokens/s
453
ms
pp1024+tg1024
4907
tokens/s
186
tokens/s
214
ms
pp1280+tg3072
4604
tokens/s
148
tokens/s
283
ms
pp384+tg1152
3843
tokens/s
205
tokens/s
104
ms
pp64+tg1024
1811
tokens/s
223
tokens/s
39
ms
pp16+tg1536
393
tokens/s
212
tokens/s
45
ms