DeepSeek-VL 1.3B
deepseek-ai/deepseek-vl-1.3b-base
Parameters
1.3B
Context
4K
Downloads
225
Likes
56
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 6.6 GB RAM 32.0 · Disk 42.8 | 9.0 GB RAM 32.0 · Disk 68.8 | 24.9 GB RAM 37.4 · Disk 107.8 |
| FP88bit | 5.1 GB RAM 32.0 · Disk 40.9 | 7.4 GB RAM 32.0 · Disk 66.9 | 23.3 GB RAM 34.9 · Disk 105.9 |
| INT88bit | 5.1 GB RAM 32.0 · Disk 40.9 | 7.4 GB RAM 32.0 · Disk 66.9 | 23.3 GB RAM 34.9 · Disk 105.9 |
| AWQ4bit | 4.4 GB RAM 32.0 · Disk 40.0 | 6.6 GB RAM 32.0 · Disk 66.0 | 22.5 GB RAM 33.7 · Disk 105.0 |
| GPTQ4bit | 4.4 GB RAM 32.0 · Disk 40.0 | 6.6 GB RAM 32.0 · Disk 66.0 | 22.5 GB RAM 33.7 · Disk 105.0 |
| GGUF4bit | 4.4 GB RAM 32.0 · Disk 40.0 | 6.6 GB RAM 32.0 · Disk 66.0 | 22.5 GB RAM 33.8 · Disk 105.0 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 1523.8 tok/s
Effective production throughput ≈ 1066.7 tok/s
score 0.6046
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5992
8× RTX 5090
256 GB VRAM
≈ 9102.2 tok/s
Effective production throughput ≈ 6371.5 tok/s
score 0.3617
1× RTX 5060 Ti
8 GB VRAM
≈ 711.1 tok/s
Effective production throughput ≈ 497.8 tok/s
score 0.673
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$20.3
/mo · vast
RTX 5060 Ti
8 GB VRAM
$39.7
/mo · vast
RTX 4070S Ti
16 GB VRAM
$49.5
/mo · vast
RTX 4080S
16 GB VRAM
$50.0
/mo · vast
RTX 5070
12 GB VRAM
$58.7
/mo · vast