Flan T5 Xxl needs about 10.6 GB of memory at Q4_K_M (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 19 quants, from 4.0 GB (Q2_K) to 44.5 GB (F32).
Flan T5 Xxl – a large language model with 11.1B parameters
Flan T5 Xxl is a 11.1B parameter T5‑based model fine‑tuned on over 1000 tasks. It supports English, German, and French. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Instruction following
- Few‑shot reasoning
- Multilingual text generation
Limits
- 512 token context window
- No vision or audio support
- Requires GPU for large quants
Best for
- Chatbot back‑end
- Content drafting
- Code generation
Who it’s for. Developers needing a powerful instruction‑tuned model for text tasks. Researchers can use the GGUF files for efficient inference on GPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.0 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_S | 4.8 GB | 5.5 GB | Fits | Get file → | |
| Q3_K | 5.3 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_M | 5.3 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_L | 5.7 GB | 6.4 GB | Fits | Get file → | |
| Q4_0 | 6.3 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_S | 6.3 GB | 7.0 GB | Fits | Get file → | |
| Q4_K | 6.8 GB | 7.5 GB | Tight | Get file → | |
| Q4_K_M | 6.8 GB | 7.5 GB | Tight | Get file → | |
| Q4_1 | 7.0 GB | 7.7 GB | Tight | Get file → | |
| Q5_0 | 7.7 GB | 8.4 GB | Too big | Get file → | |
| Q5_K_S | 7.7 GB | 8.4 GB | Too big | Get file → | |
| Q5_K | 8.0 GB | 8.7 GB | Too big | Get file → | |
| Q5_K_M | 8.0 GB | 8.7 GB | Too big | Get file → | |
| Q5_1 | 8.4 GB | 9.1 GB | Too big | Get file → | |
| Q6_K | 9.1 GB | 9.8 GB | Too big | Get file → | |
| Q8_0 | 11.8 GB | 12.5 GB | Too big | Get file → | |
| F16 | 22.3 GB | 23.0 GB | Too big | Get file → | |
| F32 | 44.5 GB | 45.2 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (6.85 GB file, 10.6 GB memory) is recommended. With 12 GB VRAM, Q5_K_M (7.96 GB file, 11.7 GB memory) fits comfortably. For 16 GB VRAM, Q6_K (9.14 GB file, 12.9 GB memory) or Q8_0 (11.83 GB file, 15.6 GB memory) are viable options.
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: the best quant that fits is Q2_K (4.0 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K (8.0 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (11.8 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (11.8 GB file, about 15.6 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (22.3 GB file, about 26.0 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (22.3 GB file, about 26.0 GB in use).
Which Flan T5 Xxl quant should you choose?
Q4_K_M is the usual starting point for Flan T5 Xxl: it balances file size and quality well. Here it is a 6.8 GB file.
The Q8_0 file is 11.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 4.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Flan T5 Xxl
How much VRAM does Flan T5 Xxl need?
About 10.6 GB at Q4_K_M with an 8K context window. That is the 6.8 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?
Yes, with Q2_K: the 4.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Flan T5 Xxl GGUF?
It depends on the quant: Q2_K is 4.0 GB, Q3_K_S is 4.8 GB, Q3_K is 5.3 GB, Q3_K_M is 5.3 GB, Q3_K_L is 5.7 GB, Q4_0 is 6.3 GB and 13 more.
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 dumb-dev/flan-t5-xxl-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 Flan T5 Xxl on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 10.6 GB of VRAM at 8k context.
Does this model support image inputs?
No, Flan T5 Xxl is a text‑only model and does not include vision capabilities.
What license applies to the GGUF files?
The GGUF files are released under the Apache‑2.0 license, same as the original model.