candle quantized flan t5 needs about 0.6 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q4_K_M) to 0.1 GB.
candle quantized flan t5 is a 77M-parameter Candle model in GGUF format, quantized by kejcao. The repository has 3 quant files, from 0.1 GB (Q4_K_M) to 0.1 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.1 GB | 0.6 GB | Fits | Get file → |
What GPU do you need for candle quantized flan t5?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
Which candle quantized flan t5 quant should you choose?
Q4_K_M is the usual starting point for candle quantized flan t5: it balances file size and quality well. Here it is a 0.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about candle quantized flan t5
How much VRAM does candle quantized flan t5 need?
About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.1 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 candle quantized flan t5 on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of candle quantized flan t5 GGUF?
It depends on the quant: Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, file is 0.1 GB.
Where can I download candle quantized flan t5 GGUF?
The files are on Hugging Face in the kejcao/candle-quantized-flan-t5 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.