← Back to community benchmarks
Qwen3-Embedding-0.6B-4bit-DWQ
Performance
1k
tokens
2,018
PP tok/s
184.8
TG tok/s
508
TTFT (ms)
1.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,018 | 184.8 | 1.0 GB | current |
| 4k | 1,864 | 106.0 | 1.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 184.8 | 1.00× |
| 2× | 275.4 | 1.49× |
| 4× | 312.4 | 1.69× |