gpurank
esc
  • Nothing named “”. Press Enter to search the offers instead.
↑↓ to move · ↵ to open · esc to close0 entries
Meta · 3D · SAM License

SAM 3D Objects

Needs 16 GB at BF16 / FP16. The smallest real configuration today is 1× T4 at Vast.ai, $0.04 per hour, about $29 a month at 730 hours.

Parameters—not published
Category3Dsized on weights + headroom
Checkpoint13 GBas released, as published
LicenseSAM Licensecheck before commercial use
ReleasedNov 19, 2025documented date
Smallest configuration · BF16 / FP16
1× T416 GB VRAM · 98% used
Per hour
$0.04
Per month
$29
Cheapest at
Vast.ai
All T4 offers →

What is documented about SAM 3D Objects

news checked 2026-10-27

Single image + mask to 3D shape, texture and layout; SAM 3D Body is the human-mesh sibling. Not in the catalogue.

  • https://huggingface.co/facebook/sam-3d-objects
  • https://huggingface.co/api/models/facebook/sam-3d-objects?blobs=true
Memory · 1 precision

How much VRAM it needs

Weights plus 20% runtime overhead. For 3d models, activations also depend on resolution, clip length and batch size; the per-GPU estimates below give the practical configuration.

PrecisionWeightsWeights + headroom
BF16 / FP16estimated13 GB16 GB
Cross-checked on Hugging Face Oct 28, 2026: repository read. Method: weights estimated from the parameter count (2, 1 and 0.6 bytes per parameter; the published checkpoint size at its own precision) x 1.2 runtime headroom; short context.
Smallest configuration per GPU · 110 GPUs · cheapest eligible on-demand offer per GPU count, every provider on file

What it costs to run, GPU by GPU

The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.

GPUSmallest configVRAM used$ / hour$ / monthCheapest at
T4Best fit1× 16 GB16 GB total98% tight$0.04$29Vast.aiTrust 78 · read Nov 1 · receipt · also iwinv $0.20, Theta EdgeCloud $0.20
Tesla P401× 24 GB24 GB total66%$0.04$30Clore.aiTrust 46 · read Nov 1 · receipt · also gcube $0.07, Vast.ai $0.11
Tesla P1001× 16 GB16 GB total98% tight$0.04$33Vast.aiTrust 78 · read Nov 1 · receipt · also gcube $0.07
RTX A40001× 16 GB16 GB total98% tight$0.06$46Clore.aiTrust 46 · read Nov 1 · receipt · also Vast.ai $0.07, Edgevana $0.10
Tesla V100 16GB1× 16 GB16 GB total98% tight$0.06$46Clore.aiTrust 46 · read Nov 1 · receipt · also Vast.ai $0.08, CloudRift $0.28
RTX A20002× 12 GB24 GB total66%$0.07$50Vast.aiTrust 78 · read Nov 1 · receipt · also Edgevana $0.12
RTX 30602× 12 GB24 GB total66%$0.07$50Vast.aiTrust 78 · read Nov 1 · receipt · also Clore.ai $0.10, Edgevana $0.12
Tesla V100 32GB1× 32 GB32 GB total49%$0.07$50Vast.aiTrust 78 · read Nov 1 · receipt · also Cyfuture AI $0.57, E2E Networks $1.50
RTX PRO 20001× 16 GB16 GB total98% tight$0.07$51Clore.aiTrust 46 · read Nov 1 · receipt · also gcube $0.16
Tesla M401× 24 GB24 GB total66%$0.07$54Clore.aiTrust 46 · read Nov 1 · receipt · also gcube $0.07
Titan Xp2× 12 GB24 GB total66%$0.08$60Vast.aiTrust 78 · read Nov 1 · receipt
RTX 5060 Ti1× 16 GB16 GB total98% tight$0.09$64Clore.aiTrust 46 · read Nov 1 · receipt · also Vast.ai $0.09, Theta EdgeCloud $0.12
RTX 30901× 24 GB24 GB total66%$0.09$66Akash NetworkTrust 53 · read Nov 1 · receipt · also Vast.ai $0.10, Clore.ai $0.11
GTX 10702× 8 GB16 GB total98% tight$0.10$70Vast.aiTrust 78 · read Nov 1 · receipt
GTX 1070 Ti2× 8 GB16 GB total98% tight$0.10$76Vast.aiTrust 78 · read Nov 1 · receipt
L41× 24 GB24 GB total66%$0.10$76Vast.aiTrust 78 · read Nov 1 · receipt · also Hikube $0.27, Infomaniak $0.28
GTX 10802× 8 GB16 GB total98% tight$0.11$79Vast.aiTrust 78 · read Nov 1 · receipt
RTX 20702× 8 GB16 GB total98% tight$0.11$79Vast.aiTrust 78 · read Nov 1 · receipt · also Edgevana $0.14
Quadro P20004× 5 GB20 GB total79%$0.11$80Vast.aiTrust 78 · read Nov 1 · receipt
RTX 3060 Ti2× 8 GB16 GB total98% tight$0.11$81Vast.aiTrust 78 · read Nov 1 · receipt · also Clore.ai $0.12, AtmosCompute $0.34
RTX A45001× 20 GB20 GB total79%$0.11$82gcubenot scored · read Nov 1 · receipt
RTX A50001× 24 GB24 GB total66%$0.12$87gcubenot scored · read Nov 1 · receipt · also GPURento $0.16, Clore.ai $0.21
RTX 2070 Super2× 8 GB16 GB total98% tight$0.12$89Vast.aiTrust 78 · read Nov 1 · receipt
RTX 40602× 8 GB16 GB total98% tight$0.12$89Vast.aiTrust 78 · read Nov 1 · receipt
The 24 cheapest of 98 GPU types that fit. Every GPU, any precision and context, in the finder