← ImageLoRA · All LoRA guides

Train a MOSS Image LoRA on 24 GB VRAM

Can you train a MOSS Image LoRA on a 24 GB GPU? Here is what the sources actually say.

Exact VRAM data we have

Official (kohya sd-scripts guide; 1024px, batch 1, LoRA dim 16, AdamW, gradient checkpointing, text encoder outputs cached): ~13 GB training with bf16 DiT, ~9 GB with ConvRot INT8 DiT + text encoder, ~5-7 GB adding block swap (needs ~15 GB system RAM). Caching text encoder outputs needs ~8.3 GB even in INT8, so 8 GB GPUs are not supported yet. Training the text encoder LoRA too: ~17 GB INT8, ~32 GB bf16. SimpleTuner ships 24, 32, 48, 80 and 144 GB recipes at 512px. Community report (ai-toolkit): ~15 GB at batch 2, 1024px, AdamW [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]

Memory-relevant settings

• sd-scripts: fp8_base is not supported for MOSS Image; use --convrot_int8 (and --convrot_int8_text_encoder) instead
• SimpleTuner recipes: rank-32 LoRA, LR 1e-4, REPA, 4,000 steps, 512px-area training; validate at 50 steps, CFG 3, 1024px
• ai-toolkit low_vram + cache_text_embeddings could OOM at startup because the text encoder stayed on the GPU; fixed in ai-toolkit on Oct 17, so update first

Trainers that support MOSS Image

• ai-toolkit: supported (SFT + Base, Oct 16; edit training Oct 17)
• kohya sd-scripts: supported (v0.12.1, Oct 18; LoRA incl. ConvRot INT8)
• SimpleTuner: supported (v4.10.0, Oct 17; Base/SFT incl. edit LoRAs)

Other tiers: 12 GB · 16 GB · MOSS Image overview

Where to rent a 24 GB+ GPU

Cheapest 24 GB+ cards (2026-10-16 14:43 UTC) from RunPod and Vast.ai. Prices move constantly; see the live price table.

Sources

• huggingface.co/OpenMOSS-Team/MOSS-Image-SFT
• huggingface.co/OpenMOSS-Team/MOSS-Image-Base
• github.com/ostris/ai-toolkit/commit/e05a3a4
• github.com/ostris/ai-toolkit/commit/c6a9b56
• github.com/ostris/ai-toolkit/commit/29f5ff4
• github.com/kohya-ss/sd-scripts/blob/main/docs/moss_image_train_network
• github.com/kohya-ss/sd-scripts/releases/tag/v0.12.1
• github.com/bghira/SimpleTuner/blob/main/documentation/quickstart/MOSS_
• github.com/bghira/SimpleTuner/releases/tag/v4.10.0
• github.com/ostris/ai-toolkit/commit/b7cd8a1
• github.com/ostris/ai-toolkit/commit/82e6311
• github.com/ostris/ai-toolkit/commit/9a1828f
• github.com/ostris/ai-toolkit/commit/8cf43dd
• huggingface.co/Comfy-Org/MOSS-Image
• huggingface.co/lodestones/MOSS-Image-SFT-8-steps-dmd
• huggingface.co/lodestones/MOSS-Image-Base-8-steps-dmd

FAQ

Is 24 GB enough to train a MOSS Image LoRA?

Yes, comfortably. kohya sd-scripts recommends the bf16 DiT with cached text encoder outputs on 24 GB, and SimpleTuner ships a 24 GB MOSS Image recipe (512px, batch 1).

What is the cheapest 24 GB+ GPU to rent?

See the table above and the live price page.

Data updated 2026-10-16. Disclosure: RunPod and Vast.ai links are referral links; ImageLoRA may earn a commission at no cost to you. unknown = not yet verified from a source.