ALIA 40b Instruct 2601 needs about 26.7 GB of memory at Q4_K_M (a 24.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.0 GB to 33.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
ALIA 40b Instruct 2601 – 40.4B parameter instruction‑tuned model
ALIA 40b Instruct 2601 is a 40.4B parameter llama‑based model trained on 9.83 trillion tokens. It is instruction‑tuned and supports long‑context up to 163840 tokens. The model is released under Apache 2.0 and is available in multiple GGUF quantizations.
Good at
- Instruction following
- Long‑context reasoning
- Multilingual text generation
Limits
- Requires large VRAM for full precision
- No vision support
- License is Apache 2.0
Best for
- Chatbot development
- Text summarization
- Code translation
Who it’s for. Developers building dialogue systems or multilingual text tools who need a large, instruction‑tuned model. Researchers wanting to experiment with long‑context LLMs may also use this model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.1 GB | Fits | Get file → | |
| IQ1_S | 9.7 GB | 11.8 GB | Too big | Get file → | |
| IQ1_M | 10.5 GB | 12.6 GB | Too big | Get file → | |
| IQ2_XXS | 11.7 GB | 13.8 GB | Too big | Get file → | |
| IQ2_XS | 12.8 GB | 14.9 GB | Too big | Get file → | |
| IQ2_S | 13.6 GB | 15.7 GB | Too big | Get file → | |
| IQ2_M | 14.5 GB | 16.7 GB | Too big | Get file → | |
| Q2_K_S | 14.7 GB | 16.8 GB | Too big | Get file → | |
| Q2_K | 15.7 GB | 17.8 GB | Too big | Get file → | |
| IQ3_XXS | 16.2 GB | 18.3 GB | Too big | Get file → | |
| IQ3_XS | 17.4 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_S | 18.2 GB | 20.3 GB | Too big | Get file → | |
| IQ3_S | 18.3 GB | 20.4 GB | Too big | Get file → | |
| IQ3_M | 18.8 GB | 21.0 GB | Too big | Get file → | |
| Q3_K_M | 20.0 GB | 22.2 GB | Too big | Get file → | |
| Q3_K_L | 21.6 GB | 23.7 GB | Too big | Get file → | |
| IQ4_XS | 22.2 GB | 24.3 GB | Too big | Get file → | |
| Q4_0 | 23.4 GB | 25.5 GB | Too big | Get file → | |
| Q4_K_S | 23.4 GB | 25.6 GB | Too big | Get file → | |
| Q4_K_M | 24.6 GB | 26.7 GB | Too big | Get file → | |
| Q4_1 | 25.7 GB | 27.8 GB | Too big | Get file → | |
| Q5_K_S | 28.1 GB | 30.2 GB | Too big | Get file → | |
| Q5_K_M | 28.8 GB | 30.9 GB | Too big | Get file → | |
| Q6_K | 33.2 GB | 35.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (9.73 GB) or Q2_K_S (14.69 GB) if you can spare more memory. For 12 GB VRAM, IQ2_S (12.77 GB) or Q3_K_S (18.2 GB) are suitable. Larger GPUs can run higher‑quality quants such as Q4_K_M (24.59 GB). Memory estimates are approximate.
What GPU do you need for ALIA 40b Instruct 2601?
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: the best quant that fits is the main file (0.0 GB file, about 2.1 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.1 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.1 GB in use).
- 12 GB VRAM: the best quant that fits is IQ1_S (9.7 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_S (13.6 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_L (21.6 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (28.8 GB file, about 30.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (33.2 GB file, about 35.3 GB in use).
Which ALIA 40b Instruct 2601 quant should you choose?
Q4_K_M is the usual starting point for ALIA 40b Instruct 2601: it balances file size and quality well. Here it is a 24.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ALIA 40b Instruct 2601
How much VRAM does ALIA 40b Instruct 2601 need?
About 26.7 GB at Q4_K_M with an 8K context window. That is the 24.6 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 2601 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ALIA 40b Instruct 2601 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 9.7 GB, IQ1_M is 10.5 GB, IQ2_XXS is 11.7 GB, IQ2_XS is 12.8 GB, IQ2_S is 13.6 GB and 18 more.
What context length does ALIA 40b Instruct 2601 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 2601 GGUF?
The files are on Hugging Face in the mradermacher/ALIA-40b-instruct-2601-i1-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 2601 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 ALIA 40b Instruct 2601 on 8 GB VRAM?
Use the IQ1_S quant which requires about 11.8 GB of VRAM at 8k context. Smaller quants are not available.
Does this model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache 2.0 license.