← Back to community benchmarks
LFM2-24B-A2B
Performance
4k
tokens
508.3
PP tok/s
53.5
TG tok/s
8061
TTFT (ms)
13.1
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 448.4 | 57.0 | 13.0 GB | view |
| 4k | 508.3 | 53.5 | 13.1 GB | current |
| 8k | 482.7 | 50.5 | 13.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.0 | 1.00× |
| 2× | 70.5 | 1.24× |
| 4× | 69.4 | 1.22× |