ComfyUI model file · Text encoder

t5xxl_fp8_e4m3fn.safetensors

T5 v1.1 XXL text encoder (fp8 e4m3fn) · Half-size T5 text encoder for FLUX.1 and SD3

t5xxl_fp8_e4m3fn.safetensors is the T5 v1.1 XXL text encoder stored in 8-bit float, half the size of fp16. It is the usual choice for FLUX.1 on machines with less than 32 GB of RAM. Put it in ComfyUI/models/text_encoders and load it in DualCLIPLoader with clip_l.

  • FLUX.1 · SD3
  • T5 v1.1 XXL
  • 4.89 GB
  • fp8

ComfyUI upcasts it as needed, so you do not need an fp8-capable GPU to use it.

t5xxl_fp8_e4m3fn.safetensors

Type
Text encoder
Format
Safetensors · fp8 (e4m3fn)
Size
4.89 GB (4,893,934,904 bytes)
SHA256
7d330da4…bfd514f09
ComfyUI folder
models/text_encoders/
Loader node
DualCLIPLoader
License
Apache-2.0
SHA256 and size from Hugging Face file metadata (comfyanonymous/flux_text_encoders), matching the Civitai API hash, checked by RunComfy on .

The short version

What is t5xxl_fp8_e4m3fn.safetensors?

This is the same T5 v1.1 XXL encoder as t5xxl_fp16, with its weights cast to the e4m3fn 8-bit float format. That halves the file to 4.89 GB and the memory it needs while encoding, for a small, usually invisible loss in prompt fidelity.

e4m3fn uses 4 exponent bits and 3 mantissa bits. The “scaled” variant, t5xxl_fp8_e4m3fn_scaled, stores extra scale factors to recover some precision for a slightly bigger file.

Install

Download and install t5xxl_fp8_e4m3fn.safetensors

Where it goes
ComfyUI/
└─ models/
   ├─ …
   └─ text_encoders/
      └─ t5xxl_fp8_e4m3fn.safetensors
terminal · Linux / macOS
$ cd ComfyUI/models/text_encoders$ wget -O t5xxl_fp8_e4m3fn.safetensors \$   https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors$ sha256sum t5xxl_fp8_e4m3fn.safetensors# 7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09

Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.

Use

How to load t5xxl_fp8_e4m3fn.safetensors in ComfyUI

FLUX.1 loads T5 next to clip_l in DualCLIPLoader (type flux). SD3 loads it in TripleCLIPLoader with clip_g and clip_l. Older video models such as CogVideoX load it alone in Load CLIP.

Minimal graph. Click a node to open its reference page.
  • Order does not matter

    DualCLIPLoader accepts T5 in either slot; the type setting decides how each is used.

  • Low on RAM?

    t5xxl_fp8_e4m3fn is half the size of fp16 with a small quality cost.

Works with

Files a FLUX.1 workflow needs

t5xxl_fp8_e4m3fn.safetensors is one part of the stack. A workflow that reports a missing model usually needs these too. FLUX.1 dev is a gated download: accept the license on Hugging Face first.

FileRoleFolderSizeDownload
flux1-dev.safetensorsDiffusion modelmodels/diffusion_models/— Get
clip_l.safetensorsText encoder (CLIP-L)models/text_encoders/246 MB Get
ae.safetensorsVAEmodels/vae/— Get

Run it

ComfyUI workflows that can use t5xxl_fp8_e4m3fn.safetensors

We match workflows by the model files they load: this exact file first, then other versions of it, then workflows built for the same use, then other models from the same family.

  1. Uses this exact file19
  2. Uses another version of this file24

Uses this exact file

19 workflows

These workflows already load t5xxl_fp8_e4m3fn.safetensors. Open one and run it as is.

Uses another version of this file

24 workflows

These workflows load a different precision or format of the same model. Select t5xxl_fp8_e4m3fn.safetensors in their DualCLIPLoader node to use this version.

Compare

Same file, other names, and alternatives

FileRelationSizeBest for
t5xxl_fp8_e4m3fn.safetensorsThis page · fp8 e4m3fn4.89 GBMachines under 32 GB RAM
t5xxl_fp8_e4m3fn_scaled.safetensorsSame encoder · fp8 scaled5.16 GBfp8 with better accuracy
t5xxl_fp16.safetensorsSame encoder · fp169.79 GBBest prompt fidelity

Troubleshoot

Common errors and fixes

Value not in list: clip_name2: 't5xxl_fp8_e4m3fn.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/text_encoders. Usually the file is missing, sits in a different folder.

Fix: Move the file into ComfyUI/models/text_encoders/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.

SafetensorError: Error while deserializing header

Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.

Fix: Check that the file is exactly 4,893,934,904 bytes and that its SHA256 matches the value above. Download it again from Hugging Face · comfyanonymous/flux_text_encoders if not.

Rather skip the setup?

Run FLUX Kontext Face Swap in your browser on a cloud GPU. Nothing to download.

Run FLUX online

FAQ

t5xxl_fp8_e4m3fn.safetensors FAQ

Will fp8 make my FLUX images worse?

Slightly, on very long or text-heavy prompts. For most prompts the result is close to fp16. If you see it, try t5xxl_fp8_e4m3fn_scaled.safetensors first.

Where do I put t5xxl_fp8_e4m3fn.safetensors in ComfyUI?

In ComfyUI/models/text_encoders/. Then refresh the node list or restart ComfyUI so DualCLIPLoader lists the file.

Which ComfyUI node loads t5xxl_fp8_e4m3fn.safetensors?

DualCLIPLoader. It is built into ComfyUI, so no custom nodes are needed.

Can I use t5xxl_fp8_e4m3fn.safetensors commercially?

Yes. T5 v1.1 XXL and this ComfyUI repackage are released under Apache-2.0.

Sources: comfyanonymous/flux_text_encoders · Civitai model 704402

RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.