← Back to community benchmarks
Qwen3-8B
Performance
1k
tokens
224.3
PP tok/s
22.0
TG tok/s
4565
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 224.3 | 22.0 | 4.9 GB | current |
| 4k | 217.5 | 19.8 | 5.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.0 | 1.00× |
| 2× | 42.2 | 1.92× |
| 4× | 53.2 | 2.42× |