Qwen/Qwen3-Embedding-0.6B
Qwen/Qwen3-Embedding-0.6B
Parameters
507.6M
Context
32K
Downloads
9M
Likes
1.3K
Architecture
qwen3
28 layers · 8 KV heads · head 128 · hidden 1024
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 2.6 GB RAM 32.0 · Disk 40.5 | 2.8 GB RAM 32.0 · Disk 66.5 | 3.2 GB RAM 32.0 · Disk 105.5 |
| FP88bit | 1.9 GB RAM 32.0 · Disk 39.7 | 2.1 GB RAM 32.0 · Disk 65.7 | 2.4 GB RAM 32.0 · Disk 104.7 |
| INT88bit | 1.9 GB RAM 32.0 · Disk 39.7 | 2.1 GB RAM 32.0 · Disk 65.7 | 2.4 GB RAM 32.0 · Disk 104.7 |
| AWQ4bit | 1.6 GB RAM 32.0 · Disk 39.4 | 1.8 GB RAM 32.0 · Disk 65.4 | 2.1 GB RAM 32.0 · Disk 104.4 |
| GPTQ4bit | 1.6 GB RAM 32.0 · Disk 39.4 | 1.8 GB RAM 32.0 · Disk 65.4 | 2.1 GB RAM 32.0 · Disk 104.4 |
| GGUF4bit | 1.6 GB RAM 32.0 · Disk 39.4 | 1.8 GB RAM 32.0 · Disk 65.4 | 2.1 GB RAM 32.0 · Disk 104.4 |
GPU Recommendations
1× RTX 3080
10 GB VRAM
≈ 6080 vec/s
Effective production throughput ≈ 4864 vectors/s
score 0.5408
1× RTX 4060 Ti
8 GB VRAM
≈ 2304 vec/s
Effective production throughput ≈ 1843.2 vectors/s
score 0.5492
8× RTX 3080
80 GB VRAM
≈ 48640 vec/s
Effective production throughput ≈ 38912 vectors/s
score 0.3667
2× RTX 3080
20 GB VRAM
≈ 12160 vec/s
Effective production throughput ≈ 9728 vectors/s
score 0.4535
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$35.7
/mo · vast
RTX 4060 Ti
8 GB VRAM
$59.2
/mo · vast
RTX 3080
10 GB VRAM
$63.8
/mo · vast
L4
24 GB VRAM
$76.2
/mo · vast
RTX 5060 Ti
8 GB VRAM
$78.3
/mo · vast