AL

ALIA 40b Instruct 2606

AliaGGUF by mradermacherUpdated 2026-07-04
Download on Hugging Face
Parameters40.4B
Context160K
Layers48
Architecturellama
Smallest quant0.0 GB
Quick answer

ALIA 40b Instruct 2606 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 2606 – a 40.4B parameter instruction‑tuned model

ALIA 40b Instruct 2606 is a 40.4B llama‑style model trained on 9.83 trillion tokens. It is optimized for instruction following, multi‑turn dialogue, and robust input handling. The model is released under Apache‑2.0.

Good at

  • Instruction following
  • Multi‑turn conversation
  • Robustness to noisy input

Limits

  • Large VRAM requirement
  • No vision support
  • Requires 8k context for full performance

Best for

  • Chatbot development
  • Text summarization
  • Language translation

Who it’s for. Developers building dialogue systems or language tools who need a large, instruction‑tuned model. Researchers interested in open‑source LLMs with strong safety alignment may also use it.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.1 GB
Fits Get file →
IQ1_S9.7 GB 11.8 GB
Too big Get file →
IQ1_M10.5 GB 12.6 GB
Too big Get file →
IQ2_XXS11.7 GB 13.8 GB
Too big Get file →
IQ2_XS12.8 GB 14.9 GB
Too big Get file →
IQ2_S13.6 GB 15.7 GB
Too big Get file →
IQ2_M14.5 GB 16.7 GB
Too big Get file →
Q2_K_S14.7 GB 16.8 GB
Too big Get file →
Q2_K15.7 GB 17.8 GB
Too big Get file →
IQ3_XXS16.2 GB 18.3 GB
Too big Get file →
IQ3_XS17.4 GB 19.5 GB
Too big Get file →
Q3_K_S18.2 GB 20.3 GB
Too big Get file →
IQ3_S18.3 GB 20.4 GB
Too big Get file →
IQ3_M18.8 GB 21.0 GB
Too big Get file →
Q3_K_M20.0 GB 22.2 GB
Too big Get file →
Q3_K_L21.6 GB 23.7 GB
Too big Get file →
IQ4_XS22.2 GB 24.3 GB
Too big Get file →
Q4_023.4 GB 25.5 GB
Too big Get file →
Q4_K_S23.4 GB 25.6 GB
Too big Get file →
Q4_K_M24.6 GB 26.7 GB
Too big Get file →
Q4_125.7 GB 27.8 GB
Too big Get file →
Q5_K_S28.1 GB 30.2 GB
Too big Get file →
Q5_K_M28.8 GB 30.9 GB
Too big Get file →
Q6_K33.2 GB 35.3 GB
Too big Get file →

For 8‑12 GB VRAM, use IQ1_S (file size 9.73 GB, estimated memory 11.8 GB at 8k context). For 12‑16 GB VRAM, IQ2_XS (file size 12.77 GB, estimated memory 14.9 GB) or Q2_K (file size 15.71 GB, estimated memory 17.8 GB). For 16‑20 GB VRAM, Q3_K_S (file size 18.2 GB, estimated memory 20.3 GB) or Q3_K_M (file size 20.04 GB, estimated memory 22.2 GB).

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: 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 2606 quant should you choose?

Q4_K_M is the usual starting point for ALIA 40b Instruct 2606: 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

Architecturellama
Parameters40.4B
Layers48
Trained context163,840 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyAlia
Licenseapache-2.0
Downloads (HF)935
Last updated2026-07-04

Frequently asked questions about ALIA 40b Instruct 2606

How much VRAM does ALIA 40b Instruct 2606 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 2606 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 2606 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 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 mradermacher/ALIA-40b-instruct-2606-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 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.

Can I run ALIA 40b Instruct 2606 on 8 GB VRAM?

No, the smallest quant requires at least 11.8 GB of VRAM at 8k context. A lower‑precision quant may reduce memory but is not available.

Does the model support image input?

No, the model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of ALIA-40b-instruct-2606

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Alia models

All Alia →

Other large models

All large models →