gpurank
esc
  • Nothing named “”. Press Enter to search the offers instead.
↑↓ to move · ↵ to open · esc to close0 entries
VAST AI · 3D · 1.5B parameters · MIT

TripoSG

Needs 2 GB at FP8 / INT8. The smallest real configuration today is 1× Quadro P2000 at Vast.ai, $0.03 per hour, about $22 a month at 730 hours.

Parameters1.5Bdense
Category3Dsized on weights + headroom
Checkpoint8 GBFP32, as published
LicenseMITcheck before commercial use
ReleasedMar 24, 2025documented date
Downloads9,790VAST-AI/TripoSG ↗
Smallest configuration · FP8 / INT8
1× Quadro P20005 GB VRAM · 36% used
Per hour
$0.03
Per month
$22
Cheapest at
Vast.ai
All Quadro P2000 offers →

What is documented about TripoSG

news checked 2026-10-27

1.5B rectified-flow shape model (HF metadata 1.44B F32). Date = HF repo creation.

  • https://huggingface.co/VAST-AI/TripoSG
  • https://huggingface.co/api/models/VAST-AI/TripoSG?blobs=true
  • https://github.com/VAST-AI-Research/TripoSG
Memory · 3 precisions

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
FP32published checkpoint8 GB10 GB
FP8 / INT8estimated2 GB2 GB
INT4 / MXFP4estimated1 GB2 GB
Cross-checked on Hugging Face Oct 28, 2026: 1.44B parameters in the safetensors headers, 8.0 GB of weight files. Method: weights as published at the native precision, verified on Hugging Face 2026-10-28; other precisions estimated at 1 (8-bit) and 0.6 (4-bit) bytes per parameter; × 1.2 runtime headroom; KV cache not added (architecture not readable).
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
Quadro P2000Best fit1× 5 GB5 GB total36%$0.03$22Vast.aiTrust 78 · read Nov 2 · receipt
RTX 30601× 12 GB12 GB total15%$0.04$26Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.05, gcube $0.05
RTX A20001× 12 GB12 GB total15%$0.04$26Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.09, Runpod $0.12
GTX 1660 Ti1× 6 GB6 GB total30%$0.04$26Vast.aiTrust 78 · read Nov 2 · receipt · also Theta EdgeCloud $0.12
GTX 10501× 2 GB2 GB total90%$0.04$27Clore.aiTrust 46 · read Nov 2 · receipt · also Akash Network $0.14
Tesla P41× 8 GB8 GB total23%$0.04$29Vast.aiTrust 78 · read Nov 2 · receipt · also Akash Network $0.06, gcube $0.07
T41× 16 GB16 GB total11%$0.04$29Vast.aiTrust 78 · read Nov 2 · receipt · also iwinv $0.20, Theta EdgeCloud $0.20
GTX 10601× 6 GB6 GB total30%$0.04$30Vast.aiTrust 78 · read Nov 2 · receipt
GTX 16601× 6 GB6 GB total30%$0.04$30Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.78
Tesla P401× 24 GB24 GB total8%$0.04$30Clore.aiTrust 46 · read Nov 2 · receipt · also gcube $0.07, Vast.ai $0.11
GTX Titan X1× 12 GB12 GB total15%$0.04$31Vast.aiTrust 78 · read Nov 2 · receipt
Titan Xp1× 12 GB12 GB total15%$0.04$31Vast.aiTrust 78 · read Nov 2 · receipt
GTX 10801× 8 GB8 GB total23%$0.04$32Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.06
Tesla P1001× 16 GB16 GB total11%$0.04$33Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.07
RTX 20601× 6 GB6 GB total30%$0.04$33gcubenot scored · read Nov 2 · receipt · also Vast.ai $0.06, Edgevana $0.08
GTX 16501× 4 GB4 GB total45%$0.05$35Vast.aiTrust 78 · read Nov 2 · receipt
GTX 10701× 8 GB8 GB total23%$0.05$36Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.08
GTX 1660 Super1× 6 GB6 GB total30%$0.05$38Theta EdgeCloudnot scored · read Nov 2 · receipt
Quadro P40001× 8 GB8 GB total23%$0.06$40Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.08
RTX 20701× 8 GB8 GB total23%$0.06$41Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.06, Clore.ai $0.21
RTX 3060 Ti1× 8 GB8 GB total23%$0.06$41Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.06, gcube $0.06
RTX 2060 Super1× 8 GB8 GB total23%$0.06$41gcubenot scored · read Nov 2 · receipt · also Clore.ai $0.06, Vast.ai $0.07
GTX 1070 Ti1× 8 GB8 GB total23%$0.06$44Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.10
RTX 2070 Super1× 8 GB8 GB total23%$0.06$44gcubenot scored · read Nov 2 · receipt · also Vast.ai $0.06, Edgevana $0.11
The 24 cheapest of 110 GPU types that fit. Every GPU, any precision and context, in the finder