AR

AREX 2 Abliterated

ArexGGUF by BoldingBuildsUpdated 2026-10-06
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant16.5 GB
Quick answer

AREX 2 Abliterated needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 16.5 GB (Q4_K_M) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

AREX 2 Abliterated – 26.9B Qwen3.8‑based agent model

AREX 2 Abliterated is a 26.9B‑parameter Qwen3.8‑derived model fine‑tuned for long‑horizon reasoning. It supports 262,144‑token context and has no vision tower. The model is released under Apache‑2.0.

Good at

  • Long‑horizon self‑improvement
  • Reasoning with tools
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is Apache‑2.0

Best for

  • Agentic reasoning tasks
  • Coding and ML engineering prompts
  • Deep research simulations

Who it’s for. Developers building autonomous agents that need extended context and reasoning. Researchers testing self‑improvement behavior in large language models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (16.55 GB file, ~19.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (19.23 GB file, ~21.9 GB memory). For 24 GB VRAM, Q8_0 (28.6 GB file, ~31.2 GB memory).

What GPU do you need for AREX 2 Abliterated?

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: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which AREX 2 Abliterated quant should you choose?

Q4_K_M is the usual starting point for AREX 2 Abliterated: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byBoldingBuilds
FamilyArex
Base modelBAAI/AREX-2
Licenseapache-2.0
Downloads (HF)1,578
Last updated2026-10-06

Frequently asked questions about AREX 2 Abliterated

How much VRAM does AREX 2 Abliterated need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 AREX 2 Abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AREX 2 Abliterated GGUF?

It depends on the quant: Q4_K_M is 16.5 GB, Q5_K_M is 19.2 GB, Q6_K is 22.1 GB, Q8_0 is 28.6 GB.

What context length does AREX 2 Abliterated support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download AREX 2 Abliterated GGUF?

The files are on Hugging Face in the BoldingBuilds/AREX-2-Abliterated-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 AREX 2 Abliterated 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 AREX 2 Abliterated on 8 GB VRAM?

Use the Q4_K_M quant; it requires about 19.2 GB memory at 8k context, so 8 GB VRAM is insufficient. You would need at least 16 GB VRAM.

Does the model support image inputs?

No, the GGUF file contains only text weights; the vision tower is not included.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of AREX-2

Similar models

Browse all →

More from BoldingBuilds

All by BoldingBuilds →

More Arex models

All Arex →

Other medium models

All medium models →