← Back to community benchmarks
LFM2-24B-A2B
Performance
16k
tokens
1,050
PP tok/s
79.4
TG tok/s
15611
TTFT (ms)
13.5
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,164 | 113.0 | 13.3 GB | view |
| 4k | 1,173 | 101.1 | 13.3 GB | view |
| 8k | 1,133 | 94.8 | 13.4 GB | view |
| 16k | 1,050 | 79.4 | 13.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 113.0 | 1.00× |
| 2× | 166.7 | 1.48× |
| 4× | 207.7 | 1.84× |
| 8× | 223.0 | 1.97× |