← Back to community benchmarks
Llama-3.1-8B-Instruct
Performance
1k
tokens
188.3
PP tok/s
20.0
TG tok/s
5443
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 188.3 | 20.0 | 4.9 GB | current |
| 4k | 184.5 | 17.9 | 5.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.0 | 1.00× |
| 2× | 35.0 | 1.75× |
| 4× | 70.2 | 3.51× |