Related Models
Performance
526
tokens/sec
Faster than 99% of models
1.19
seconds
Faster than 46% of models
1.19
seconds
Faster than 63% of models
Market Median
95 tok/s
455% faster
Median TTFT
1.11s
7% slower
Speed Comparison
LFM2.5-VL-1.6B
519 tok/s-1%
LFM2 1.2B
518 tok/s-1%
Granite 4.0 H Small
481 tok/s-9%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
32.6%
HLE
6.8%
LiveCodeBenchNot evaluated
SciCode
2.3%
TerminalBench Hard
0.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
43.8%
Long Context Recall
0.0%
Tau2
10.8%
Market AverageTop Score