flan-t5-xxl needs about 8.8 GB of memory at Q8_0 (a 5.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 5.1 GB (Q8_0) to 19.1 GB (F32).
Flan T5 XXL encoder-only model for text encoding tasks
Flan T5 XXL encoder-only model with 4.76 billion parameters. Trained on 512‑token context windows. Released under Apache‑2.0 license.
Good at
- Text encoding
- Feature extraction
- Coding support
Limits
- 512‑token context only
- No vision or multimodal support
- Requires 8.8 GB VRAM for Q8_0
Best for
- Embedding generation
- Semantic search
- Code analysis
Who it’s for. Developers needing high‑capacity text embeddings or code‑related analysis. Suitable for research and production pipelines that can allocate sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 5.1 GB | 5.8 GB | Fits | Get file → | |
| F32 | 19.1 GB | 19.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q8_0 (5.06 GB file, 8.8 GB memory). If more memory is available, F32 provides higher precision but needs 22.8 GB VRAM.
What GPU do you need for flan-t5-xxl?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q8_0 (5.1 GB file, about 8.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (5.1 GB file, about 8.8 GB in use).
- 24 GB VRAM: the best quant that fits is F32 (19.1 GB file, about 22.8 GB in use).
Which flan-t5-xxl quant should you choose?
Q8_0 (5.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about flan-t5-xxl
How much VRAM does flan-t5-xxl need?
About 8.8 GB at Q8_0 with an 8K context window. That is the 5.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run flan-t5-xxl on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of flan-t5-xxl GGUF?
It depends on the quant: Q8_0 is 5.1 GB, F32 is 19.1 GB.
What context length does flan-t5-xxl support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 3.2 GB at 8K and 0.2 GB at 512.
Where can I download flan-t5-xxl GGUF?
The files are on Hugging Face in the silveroxides/flan-t5-xxl-encoder-only-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does flan-t5-xxl use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, using the Q8_0 quantization which requires 8.8 GB VRAM. It is close to the limit, so a GPU with 8 GB may struggle.
Does this model support vision tasks?
No, it is an encoder-only text model with no vision capabilities.
What license applies to this model?
Apache‑2.0, allowing free use and modification.