MOSS-Image-SFT
Needs 7 GB at FP8 / INT8. The smallest real configuration today is 1× RTX 3060 at Vast.ai, $0.04 per hour, about $26 a month at 730 hours.
- Per hour
- $0.04
- Per month
- $26
- Cheapest at
Vast.ai
What is documented about MOSS-Image-SFT
news checked 2026-10-275B single-stream DiT trained with Muon; strong Chinese/English text rendering and JSON layout control. Files: transformer 10.17 GB BF16, text encoder 16.79 GB (Qwen3.5 architecture; Qwen3.5-9B per README comment and the Kromoss card), VAE 0.25 GB (FLUX.2 small decoder). 50 steps default. Day-0 support in SGLang, vLLM-Omni and ComfyUI (Comfy-Org/MOSS-Image: BF16 10.17 GB, INT8 5.41 GB). Comfy-Org repo had 2.4M downloads by 2026-10-27; many community LoRAs, including an editing LoRA (chinoll/Moss-Image-Edit). GitHub news: weights public 2026-10-16 (HF repos created 2026-10-11); tech report arXiv 2610.23374 (2026-10-19).
- https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT
- https://huggingface.co/api/models/OpenMOSS-Team/MOSS-Image-SFT?blobs=true
- https://github.com/OpenMOSS/MOSS-Image
Memory · 3 precisionsHow much VRAM it needs
Weights plus 20% runtime overhead. For image generation models, activations also depend on resolution, clip length and batch size; the per-GPU estimates below give the practical configuration.
| Precision | Weights | Weights + headroom |
|---|---|---|
| BF16published checkpoint | 27 GB | 33 GB |
| FP8 / INT8estimated | 5 GB | 7 GB |
| INT4 / MXFP4estimated | 3 GB | 4 GB |
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 |
|---|---|---|---|---|---|
| RTX 3060Best fit | 1× 12 GB12 GB total | 51% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.05, gcube $0.05 |
| RTX A2000 | 1× 12 GB12 GB total | 51% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.09, Runpod $0.12 |
| Tesla P4 | 1× 8 GB8 GB total | 76% | $0.04 | $29 | Vast.aiTrust 78 · read Nov 2 · receipt · also Akash Network $0.06, gcube $0.07 |
| T4 | 1× 16 GB16 GB total | 38% | $0.04 | $29 | Vast.aiTrust 78 · read Nov 2 · receipt · also iwinv $0.20, Theta EdgeCloud $0.20 |
| Tesla P40 | 1× 24 GB24 GB total | 25% | $0.04 | $30 |  Clore.aiTrust 49 · read Nov 2 · receipt · also gcube $0.07, Vast.ai $0.11 |
| GTX Titan X | 1× 12 GB12 GB total | 51% | $0.04 | $31 | Vast.aiTrust 78 · read Nov 2 · receipt |
| Titan Xp | 1× 12 GB12 GB total | 51% | $0.04 | $31 | Vast.aiTrust 78 · read Nov 2 · receipt |
| GTX 1080 | 1× 8 GB8 GB total | 76% | $0.04 | $32 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.06 |
| Tesla P100 | 1× 16 GB16 GB total | 38% | $0.04 | $33 | Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.07 |
| GTX 1070 | 1× 8 GB8 GB total | 76% | $0.05 | $36 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.08 |
| Quadro P4000 | 1× 8 GB8 GB total | 76% | $0.06 | $40 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.08 |
| RTX 2070 | 1× 8 GB8 GB total | 76% | $0.06 | $41 | Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.06, Clore.ai $0.21 |
| RTX 3060 Ti | 1× 8 GB8 GB total | 76% | $0.06 | $41 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.06, gcube $0.06 |
| RTX 2060 Super | 1× 8 GB8 GB total | 76% | $0.06 | $41 | |
| Quadro P2000 | 2× 5 GB10 GB total | 61% | $0.06 | $41 | Vast.aiTrust 78 · read Nov 2 · receipt |
| GTX 1070 Ti | 1× 8 GB8 GB total | 76% | $0.06 | $44 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.10 |
| RTX 2070 Super | 1× 8 GB8 GB total | 76% | $0.06 | $44 | |
| RTX 3070 | 1× 8 GB8 GB total | 76% | $0.06 | $44 | |
| RTX 4060 | 1× 8 GB8 GB total | 76% | $0.06 | $45 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.08, Theta EdgeCloud $0.09 |
| Tesla V100 16GB | 1× 16 GB16 GB total | 38% | $0.06 | $46 | Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $0.08, CloudRift $0.28 |
| RTX 2080 | 1× 8 GB8 GB total | 76% | $0.06 | $47 | |
| RTX 2080 Super | 1× 8 GB8 GB total | 76% | $0.06 | $47 | |
| GTX 1080 Ti | 1× 11 GB11 GB total | 55% | $0.06 | $47 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.08 |
| RTX 2080 Ti | 1× 11 GB11 GB total | 55% | $0.07 | $49 | |
| The 24 cheapest of 103 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
MOSS-Image-SFT · related