Tencent · 3D · MIT
Pixal3D
Needs 56 GB at BF16 / FP16. The smallest real configuration today is 2× Tesla V100 32GB at Vast.ai, $0.14 per hour, about $99 a month at 730 hours.
Parameters—not published
Category3Dsized on weights + headroom
Checkpoint46 GBas released, as published
LicenseMITcheck before commercial use
Released—documented date
Smallest configuration · BF16 / FP16
2× Tesla V100 32GB64 GB VRAM · 86% used
- Per hour
- $0.14
- Per month
- $99
- Cheapest at
Vast.ai
What is documented about Pixal3D
news checked 2026-10-27SIGGRAPH 2026 pixel-aligned image-to-3D; inference code released May 2026 with an improved TRELLIS.2-based version (paper version based on Direct3D-S2). checkpoint_gb = whole ckpts folder (both versions). HF repo created 2026-04-30; exact public date not stated (README says May 2026). Comfy-Org/Pixal3D had 735K downloads. NOT in the 2026-10-04 catalogue.
- https://huggingface.co/TencentARC/Pixal3D
- https://huggingface.co/api/models/TencentARC/Pixal3D?blobs=true
- https://huggingface.co/api/models/Comfy-Org/Pixal3D?blobs=true
Memory · 1 precisionHow 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.
| Precision | Weights | Weights + headroom |
|---|---|---|
| BF16 / FP16estimated | 46 GB | 56 GB |
Cross-checked on Hugging Face Oct 28, 2026: repository read, 46.0 GB of weight files. 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 · 109 GPUs · cheapest eligible on-demand offer per GPU count, every provider on fileWhat 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.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| Tesla V100 32GBBest fit | 2× 32 GB64 GB total | 86% | $0.14 | $99 | Vast.aiTrust 78 · read Nov 2 · receipt · also Cyfuture AI $1.13, io.net $2.52 |
| Tesla P100 | 4× 16 GB64 GB total | 86% | $0.19 | $142 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.43 |
| RTX 3090 | 4× 24 GB96 GB total | 58% | $0.25 | $183 |  Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $0.56, Edgevana $0.92 |
| RTX 5060 Ti | 4× 16 GB64 GB total | 86% | $0.35 | $258 | Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $0.40, Edgevana $0.68 |
| RTX A4000 | 4× 16 GB64 GB total | 86% | $0.36 | $266 | Vast.aiTrust 78 · read Nov 2 · receipt · also AtmosCompute $0.66, Spheron $3.84 |
| RTX A6000 | 2× 48 GB96 GB total | 58% | $0.38 | $274 | Clore.aiTrust 49 · read Nov 2 · receipt · also Lium $0.84, Spheron $0.89 |
| Tesla V100 16GB | 4× 16 GB64 GB total | 86% | $0.38 | $275 | Vast.aiTrust 78 · read Nov 2 · receipt · also CloudRift $1.00, AtmosCompute $1.30 |
| Quadro RTX 5000 | 4× 16 GB64 GB total | 86% | $0.40 | $294 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 3060 | 8× 12 GB96 GB total | 58% | $0.43 | $312 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.64, AtmosCompute $1.01 |
| A800 80GB PCIe | 1× 80 GB80 GB total | 69% | $0.47 | $342 | Vast.aiTrust 78 · read Nov 2 · receipt |
| Quadro RTX 8000 | 2× 48 GB96 GB total | 58% | $0.48 | $354 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.56 |
| RTX 3070 | 8× 8 GB64 GB total | 86% | $0.50 | $364 | Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $5.23 |
| L40 | 2× 48 GB96 GB total | 58% | $0.54 | $391 | Vast.aiTrust 78 · read Nov 2 · receipt · also io.net $1.32, GPU.ai $1.56 |
| RTX 2080 Ti | 8× 11 GB88 GB total | 63% | $0.59 | $432 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.68 |
| T4 | 4× 16 GB64 GB total | 86% | $0.59 | $434 | Vast.aiTrust 78 · read Nov 2 · receipt · also iwinv $0.78, NHN Cloud $2.46 |
| A100 80GB | 1× 80 GB80 GB total | 69% | $0.60 | $440 | Vast.aiTrust 78 · read Nov 2 · receipt · also packet.ai $0.89, GPUBank $0.95 |
| RTX 5060 | 8× 8 GB64 GB total | 86% | $0.65 | $472 | Clore.aiTrust 49 · read Nov 2 · receipt |
| RTX PRO 6000 | 1× 96 GB96 GB total | 58% | $0.66 | $482 |  packet.ainot scored · read Nov 2 · receipt · also Runpod $0.69, HyperAI $0.80 |
| Titan RTX | 4× 24 GB96 GB total | 58% | $0.70 | $508 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 5070 Ti | 4× 16 GB64 GB total | 86% | $0.70 | $508 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.80, Edgevana $0.80 |
| RTX 4070 Ti Super | 4× 16 GB64 GB total | 86% | $0.75 | $548 | Clore.aiTrust 49 · read Nov 2 · receipt · also AtmosCompute $1.54 |
| L40S | 2× 48 GB96 GB total | 58% | $0.76 | $555 |  LiumTrust 40 · read Nov 2 · receipt · also Vast.ai $1.07, CloudRift $1.26 |
| A100 40GB | 2× 40 GB80 GB total | 69% | $0.77 | $566 | Vast.aiTrust 78 · read Nov 2 · receipt · also iwinv $1.83, AtmosCompute $1.93 |
| RTX 5090 | 2× 32 GB64 GB total | 86% | $0.80 | $586 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.96, Edgevana $1.35 |
| The 24 cheapest of 69 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
Pixal3D · related