gemma_3_12B_it_fp4_mixed.safetensors
Gemma 3 12B IT FP4 Mixed (Text Encoder)
FP4-mixed Gemma 3 12B IT text encoder (~90% FP4 layers). Required for 16-24 GB ComfyUI workflows. Place in models/text_encoders/.
Download gemma_3_12B_it_fp4_mixed.safetensors
Direct HuggingFace download. 9.5 GB · Free.
No 8GB GPU? Try gemma_3_12B_it_fp4_mixed.safetensors online — free generation included
Skip the 9.5 GB download and ComfyUI setup. Generate a 6-second video using this exact model in your browser, ~30 seconds.
Will this run on my GPU?
Minimum: 8GB VRAM.
Recommendation: Use this on 16/24 GB VRAM cards. Full BF16 Gemma OOMs alongside the transformer.
How to use gemma_3_12B_it_fp4_mixed.safetensors
- Download the file from HuggingFace.
- Place it in ComfyUI/models/loras/ inside your ComfyUI directory.
- Restart ComfyUI (or refresh the model list from the menu).
- Load a compatible workflow — see below.
Don't want to run this locally? Try gemma_3_12B_it_fp4_mixed.safetensors online with a free generation — no GPU, no install, ~30 seconds per clip.
Common issues
ComfyUI doesn't see the file after I downloaded it▼
Make sure the file is in ComfyUI/models/loras/ (not a subfolder). Restart ComfyUI fully — the menu refresh sometimes misses new files. Filename must match exactly: gemma_3_12B_it_fp4_mixed.safetensors.
CUDA out of memory error when loading the model▼
gemma_3_12B_it_fp4_mixed.safetensors needs ~8GB VRAM minimum. If you're hitting OOM: • Enable Sequential Offloading in ComfyUI settings • Lower the resolution (768×512 instead of 1280×704) — both dimensions must be divisible by 32 • Reduce frame count (65 frames instead of 161) — must be 8n+1 • Use a smaller variant — see Related models below.
How do I apply this LoRA in ComfyUI?▼
Load it in a 'LoraLoader' node and connect it after your model loader. Pair this LoRA with the dev base model (not the distilled one) for the right behavior. LoRA strength 1.0 is the trained value — start there.
Get notified when Gemma 3 12B IT FP4 Mixed (Text Encoder) updates
Occasional updates on what's new in LTX 2.3 — new FP8 quants, LoRAs, IC-LoRA releases — with our hands-on verdict on whether they're worth re-downloading. No fixed cadence.
No spam. Sent occasionally when there's real news. Unsubscribe in one click.
Related models
ltx-2.3-22b-distilled-1.1_lora-dynamic_fro09_avg_rank_111_bf16.safetensors
ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors
ltx-2.3-22b-distilled-lora-384-1.1.safetensors
ltx-2.3-22b-distilled-lora-384.safetensors
ltx-2.3-22b-distilled-lora-dynamic_fro09_avg_rank_105_bf16.safetensors
ltx-2.3-spatial-upscaler-x1.5-1.0.safetensors