Qwen/Qwen3-0.6B
Qwen/Qwen3-0.6B
Parameters
507.9M
Context
40K
Downloads
29.6M
Likes
1.7K
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 | 4.4 GB RAM 32.0 · Disk 40.5 | 13.6 GB RAM 32.0 · Disk 66.5 | 79.3 GB RAM 119.0 · Disk 105.5 |
| FP88bit | 3.8 GB RAM 32.0 · Disk 39.7 | 13.0 GB RAM 32.0 · Disk 65.7 | 78.7 GB RAM 118.0 · Disk 104.7 |
| INT88bit | 3.8 GB RAM 32.0 · Disk 39.7 | 13.0 GB RAM 32.0 · Disk 65.7 | 78.7 GB RAM 118.0 · Disk 104.7 |
| AWQ4bit | 3.5 GB RAM 32.0 · Disk 39.4 | 12.7 GB RAM 32.0 · Disk 65.4 | 78.3 GB RAM 117.5 · Disk 104.4 |
| GPTQ4bit | 3.5 GB RAM 32.0 · Disk 39.4 | 12.7 GB RAM 32.0 · Disk 65.4 | 78.3 GB RAM 117.5 · Disk 104.4 |
| GGUF4bit | 3.5 GB RAM 32.0 · Disk 39.4 | 12.7 GB RAM 32.0 · Disk 65.4 | 78.4 GB RAM 117.5 · Disk 104.4 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 7168 tok/s
Effective production throughput ≈ 5017.6 tok/s
score 0.6024
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6771
8× H200 SXM
1128 GB VRAM
≈ 61440 tok/s
Effective production throughput ≈ 43008 tok/s
score 0.2197
1× RTX 3090
24 GB VRAM
≈ 3744 tok/s
Effective production throughput ≈ 2620.8 tok/s
score 0.6358
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$66.7
/mo · vast
RTX 3090
24 GB VRAM
$88.4
/mo · vast
RTX PRO 4000
16 GB VRAM
$127
/mo · vast
RTX 4070S Ti
16 GB VRAM
$138
/mo · vast
RTX 4080S
16 GB VRAM
$157
/mo · vast