ALIA 40b fc 2607 needs about 26.6 GB of memory at Q4_0 (a 23.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 23.3 GB (Q4_0) to 43.0 GB (Q8_0).
ALIA 40b fc 2607 is a 40.4B-parameter Alia model in GGUF format, quantized by BSC-LT. Its trained context length is 160K tokens. The repository has 2 quant files, from 23.3 GB (Q4_0) to 43.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 23.3 GB | 26.6 GB | Too big | Get file → | |
| Q8_0 | 43.0 GB | 48.6 GB | Too big | Get file → |
What GPU do you need for ALIA 40b fc 2607?
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: 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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_0 (23.3 GB file, about 26.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_0 (23.3 GB file, about 26.6 GB in use).
Which ALIA 40b fc 2607 quant should you choose?
Q4_0 (23.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ALIA 40b fc 2607
How much VRAM does ALIA 40b fc 2607 need?
About 26.6 GB at Q4_0 with an 8K context window. That is the 23.3 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 ALIA 40b fc 2607 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ALIA 40b fc 2607 GGUF?
It depends on the quant: Q4_0 is 23.3 GB, Q8_0 is 43.0 GB.
What context length does ALIA 40b fc 2607 support?
The GGUF header lists a trained context length of 163,840 tokens (160K).
Where can I download ALIA 40b fc 2607 GGUF?
The files are on Hugging Face in the BSC-LT/ALIA-40b-fc-2607-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 ALIA 40b fc 2607 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.