← Back to community benchmarks
Qwen3-VL-Embedding-2B
Performance
1k
tokens
792.0
PP tok/s
25.5
TG tok/s
1294
TTFT (ms)
4.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 792.0 | 25.5 | 4.4 GB | current |
| 4k | 948.3 | 23.6 | 4.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.5 | 1.00× |
| 2× | 34.9 | 1.37× |
| 4× | 53.9 | 2.11× |