← Back to community benchmarks
Qwen3-Embedding-4B-4bit-DWQ
Performance
1k
tokens
384.4
PP tok/s
38.7
TG tok/s
2667
TTFT (ms)
2.7
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 | 384.4 | 38.7 | 2.7 GB | current |
| 4k | 348.4 | 32.3 | 3.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.7 | 1.00× |
| 2× | 72.9 | 1.88× |
| 4× | 87.8 | 2.27× |