AB

A.X 4.0 Abliterated

AbliteratedGGUF by mradermacherUpdated 2025-12-25
Download on Hugging Face
Parameters71.9B
Context128K
Layers80
Architectureqwen2
Smallest quant0.0 GB
Quick answer

A.X 4.0 Abliterated needs about 50.0 GB of memory at Q4_K_M (a 46.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 21 quants, from 0.0 GB to 46.9 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

A.X 4.0 Abliterated – 71.9B Qwen2 model in GGUF format

A.X 4.0 Abliterated is a 71.9B parameter Qwen2 model. It supports reasoning and tool usage. The model is available in multiple quantizations for different memory budgets.

Good at

  • Reasoning
  • Tool usage
  • Large context support

Limits

  • No vision support
  • License not specified
  • No mixture of experts

Best for

  • Complex reasoning tasks
  • Tool‑integrated workflows
  • Long‑form content generation

Who it’s for. Developers and researchers needing a large‑scale Qwen2 model with reasoning and tool capabilities. Suitable for applications that can accommodate the required VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.2 GB
Fits Get file →
IQ1_S22.3 GB 25.5 GB
Too big Get file →
IQ1_M23.3 GB 26.5 GB
Too big Get file →
IQ2_XXS25.1 GB 28.3 GB
Too big Get file →
IQ2_XS26.6 GB 29.8 GB
Too big Get file →
IQ2_S27.5 GB 30.7 GB
Too big Get file →
IQ2_M28.9 GB 32.1 GB
Too big Get file →
Q2_K_S29.1 GB 32.3 GB
Too big Get file →
Q2_K29.3 GB 32.5 GB
Too big Get file →
IQ3_XXS31.4 GB 34.6 GB
Too big Get file →
IQ3_XS32.3 GB 35.5 GB
Too big Get file →
IQ3_S34.0 GB 37.2 GB
Too big Get file →
Q3_K_S34.0 GB 37.2 GB
Too big Get file →
IQ3_M35.0 GB 38.2 GB
Too big Get file →
Q3_K_M37.2 GB 40.4 GB
Too big Get file →
Q3_K_L39.0 GB 42.2 GB
Too big Get file →
IQ4_XS39.2 GB 42.3 GB
Too big Get file →
Q4_040.8 GB 44.0 GB
Too big Get file →
Q4_K_S43.3 GB 46.5 GB
Too big Get file →
Q4_145.1 GB 48.3 GB
Too big Get file →
Q4_K_M46.9 GB 50.0 GB
Too big Get file →

For 8 GB VRAM use the IQ1_S quant (22.28 GB file, 25.5 GB memory at 8 k context). For 12 GB VRAM use IQ1_M (23.33 GB file, 26.5 GB memory). For 16 GB VRAM use IQ2_XXS (25.08 GB file, 28.3 GB memory).

What GPU do you need for A.X 4.0 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: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_S (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (43.3 GB file, about 46.5 GB in use).

Which A.X 4.0 Abliterated quant should you choose?

Q4_K_M is the usual starting point for A.X 4.0 Abliterated: it balances file size and quality well. Here it is a 46.9 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

Architectureqwen2
Parameters71.9B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
Downloads (HF)714
Last updated2025-12-25

Frequently asked questions about A.X 4.0 Abliterated

How much VRAM does A.X 4.0 Abliterated need?

About 50.0 GB at Q4_K_M with an 8K context window. That is the 46.9 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 A.X 4.0 Abliterated on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of A.X 4.0 Abliterated GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 22.3 GB, IQ1_M is 23.3 GB, IQ2_XXS is 25.1 GB, IQ2_XS is 26.6 GB, IQ2_S is 27.5 GB and 15 more.

What context length does A.X 4.0 Abliterated support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download A.X 4.0 Abliterated GGUF?

The files are on Hugging Face in the mradermacher/A.X-4.0-abliterated-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the IQ1_S quant requires about 25.5 GB memory at 8 k context, which fits 8 GB VRAM with efficient batching.

Does this model support vision?

No, the model does not have vision capabilities.

What is the context length?

The model was trained with 131072 tokens of context.

Other GGUFs of A.X-4.0-abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Abliterated models

All Abliterated →

Other large models

All large models →