TEST #2900 RESULTS
02/25/2026 - 6:56 PM
ACCELERATOR
MODEL
135
tokens/s
generation
538
ms
time to first token
2105
tokens/s
prompt
808
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Max 8P+4E
RAM
32GB
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 20:53:05 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2757
tokens/s
154
tokens/s
378
ms
pp4096+tg256
2475
tokens/s
95.6
tokens/s
1.67
sec
pp2048+tg256
2634
tokens/s
126
tokens/s
785
ms
pp2048+tg768
2640
tokens/s
121
tokens/s
784
ms
pp1024+tg1024
2602
tokens/s
140
tokens/s
400
ms
pp1280+tg3072
2573
tokens/s
113
tokens/s
504
ms
pp384+tg1152
2190
tokens/s
151
tokens/s
181
ms
pp64+tg1024
794
tokens/s
164
tokens/s
86
ms
pp16+tg1536
283
tokens/s
151
tokens/s
62
ms