← Back to community benchmarks
Qwen3-8B
Performance
4k
tokens
177.6
PP tok/s
15.1
TG tok/s
23060
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.7rc2
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 183.9 | 18.2 | 4.9 GB | view |
| 4k | 177.6 | 15.1 | 5.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.2 | 1.00× |
| 2× | 34.4 | 1.89× |
| 4× | 39.7 | 2.18× |