ESS AIST 81M preview needs about 0.6 GB of memory at Q5_1 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.1 GB (Q5_1) to 0.1 GB (Q8_0).
ESS AIST 81M preview is a 81M-parameter Ess model in GGUF format, quantized by augmem. The repository has 2 quant files, from 0.1 GB (Q5_1) to 0.1 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_1 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → |
What GPU do you need for ESS AIST 81M preview?
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 Q8_0 (0.1 GB file, about 0.6 GB in use).
Which ESS AIST 81M preview quant should you choose?
Q5_1 (0.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ESS AIST 81M preview
How much VRAM does ESS AIST 81M preview need?
About 0.6 GB at Q5_1 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 ESS AIST 81M preview on an 8 GB GPU?
Yes, with Q8_0: 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 ESS AIST 81M preview GGUF?
It depends on the quant: Q5_1 is 0.1 GB, Q8_0 is 0.1 GB.
Where can I download ESS AIST 81M preview GGUF?
The files are on Hugging Face in the augmem/ESS-AIST-81M-preview repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does ESS AIST 81M preview 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.