← Back to community benchmarks
LFM2-24B-A2B
Performance
4k
tokens
607.8
PP tok/s
61.1
TG tok/s
6741
TTFT (ms)
13.1
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 592.7 | 63.7 | 13.0 GB | view |
| 4k | 607.8 | 61.1 | 13.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.7 | 1.00× |
| 2× | 92.4 | 1.45× |
| 4× | 102.8 | 1.61× |
| 8× | 107.2 | 1.68× |