| File | llava_llama3_fp8_scaled.safetensors |
| What it is | LLaVA-Llama3 FP8 (scaled) (text encoder) |
| Size | 9.1 GB |
| Folder | ComfyUI/models/text_encoders/ |
| Loader node | a text-encoder loader: Load CLIP (CLIPLoader) for one encoder, DualCLIPLoader when the model takes two (FLUX.1: CLIP-L + T5-XXL) |
| Source | Comfy-Org/HunyuanVideo_repackaged on Hugging Face |
Download llava_llama3_fp8_scaled.safetensors (9.1 GB)
Where to put it
Put the file in ComfyUI/models/text_encoders/ (in the portable version: ComfyUI_windows_portable/ComfyUI/models/text_encoders/). Older guides say models/clip: that folder still works. Then press R in ComfyUI, or restart it, so the file shows up in a text-encoder loader: Load CLIP (CLIPLoader) for one encoder, DualCLIPLoader when the model takes two (FLUX.1: CLIP-L + T5-XXL).
If a workflow says “Value not in list” for this node, the file name in the workflow is different from yours, or the file is in another folder. Click the node and pick the file from the list.
What it does
A text encoder turns your prompt into numbers the model understands. It runs once per prompt, then ComfyUI can move it out of VRAM to make room for the image model — so it costs load time and system RAM more than speed.
This is a smaller FP8 version. It loads faster and needs about half the RAM of the 16-bit file; the difference in the pictures is usually hard to see. It is the version this site lists by default.
FP8 files load on every NVIDIA card in ComfyUI. On a Mac (Apple Silicon) FP8 does not load — use the 16-bit file there.
Models that use llava_llama3_fp8_scaled.safetensors
| Model | Type | Fits from | Runs well from |
|---|---|---|---|
| HunyuanVideo (13B, original) | video | 11 GB | 18 GB |
VRAM of the graphics card, for the model with the file this site picks for that card. Open a model to see every file and every GPU.
Other versions of this text encoder
| File | Precision | Size | Used by |
|---|---|---|---|
| llava_llama3_fp8_scaled.safetensors | FP8 | 9.1 GB | 1 model |
| llava_llama3_fp16.safetensors | FP16 | 16.1 GB | 1 model |
Same encoder, different precision. Any of them works in the same loader node; pick one and select it in the node.
Not sure your card can run these models? Check your GPU. All shared files: ComfyUI model files.
Size and source read from Hugging Face (2026-10-01).