lpiccinelli/unidepth-v2-vitl14
lpiccinelli/unidepth-v2-vitl14
Parameters
353.8M
Context
—
Downloads
36.7M
Likes
50
Architecture
—
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 5.8 GB RAM 32.0 · Disk 40.0 | 21.6 GB RAM 32.4 · Disk 66.0 | 118.5 GB RAM 177.8 · Disk 105.0 |
| FP88bit | 5.4 GB RAM 32.0 · Disk 39.5 | 21.1 GB RAM 32.0 · Disk 65.5 | 118.1 GB RAM 177.1 · Disk 104.5 |
| INT88bit | 5.4 GB RAM 32.0 · Disk 39.5 | 21.1 GB RAM 32.0 · Disk 65.5 | 118.1 GB RAM 177.1 · Disk 104.5 |
| AWQ4bit | 5.2 GB RAM 32.0 · Disk 39.3 | 20.9 GB RAM 32.0 · Disk 65.3 | 117.8 GB RAM 176.8 · Disk 104.3 |
| GPTQ4bit | 5.2 GB RAM 32.0 · Disk 39.3 | 20.9 GB RAM 32.0 · Disk 65.3 | 117.8 GB RAM 176.8 · Disk 104.3 |
| GGUF4bit | 5.2 GB RAM 32.0 · Disk 39.3 | 20.9 GB RAM 32.0 · Disk 65.3 | 117.8 GB RAM 176.8 · Disk 104.3 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 10541.2 tok/s
Effective production throughput ≈ 7378.8 tok/s
score 0.6721
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.621
8× H200 SXM
1128 GB VRAM
≈ 90352.9 tok/s
Effective production throughput ≈ 63247 tok/s
score 0.2197
1× RTX 3090
24 GB VRAM
≈ 5505.9 tok/s
Effective production throughput ≈ 3854.1 tok/s
score 0.6632
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3090
24 GB VRAM
$45.4
/mo · vast
RTX 4090
24 GB VRAM
$98.1
/mo · vast
RTX 4090D
24 GB VRAM
$117
/mo · vast
L4
24 GB VRAM
$148
/mo · vast
A10
24 GB VRAM
$176
/mo · vast