← Back to community benchmarks
LFM2-24B-A2B
Performance
1k
tokens
625.8
PP tok/s
71.3
TG tok/s
1638
TTFT (ms)
13.0
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 625.8 | 71.3 | 13.0 GB | current |
| 4k | 603.2 | 72.2 | 13.1 GB | view |
| 8k | 614.2 | 65.6 | 13.1 GB | view |
| 16k | 583.7 | 59.6 | 13.3 GB | view |
| 32k | 523.3 | 47.6 | 13.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 71.3 | 1.00× |
| 2× | 106.2 | 1.49× |
| 4× | 124.0 | 1.74× |