← Back to community benchmarks
qwen3-8b
Performance
1k
tokens
266.7
PP tok/s
24.6
TG tok/s
3839
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M1 (7c)
Memory
8 GB
GPU Cores
7
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 266.7 | 24.6 | 2.9 GB | current |
| 4k | 264.3 | 23.3 | 3.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.6 | 1.00× |
| 2× | 37.2 | 1.51× |
| 4× | 35.6 | 1.45× |