ALIA-40b-instruct-2606 needs about 45.1 GB of memory at Q8_0 (a 43.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
ALIA-40b-instruct-2606 is a 40.4B-parameter Alia model in GGUF format, quantized by BSC-LT. Its trained context length is 160K tokens. The repository has 1 quant file, from 43.0 GB (Q8_0) to 43.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 43.0 GB | 45.1 GB | Too big | Get file → |
What GPU do you need for ALIA-40b-instruct-2606?
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: 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: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q8_0 (43.0 GB file, about 45.1 GB in use).
Which ALIA-40b-instruct-2606 quant should you choose?
Q8_0 (43.0 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
Source
Frequently asked questions about ALIA-40b-instruct-2606
How much VRAM does ALIA-40b-instruct-2606 need?
About 45.1 GB at Q8_0 with an 8K context window. That is the 43.0 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-instruct-2606 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 45.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ALIA-40b-instruct-2606 GGUF?
It depends on the quant: Q8_0 is 43.0 GB.
What context length does ALIA-40b-instruct-2606 support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download ALIA-40b-instruct-2606 GGUF?
The files are on Hugging Face in the BSC-LT/ALIA-40b-instruct-2606-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-instruct-2606 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.