AX

A.X 3.1

GGUFGGUF by jaesang-leeUpdated 2026-04-06
Download on Hugging Face
Parameters34.7B
Context32K
Layers48
Architecturellama
Smallest quant22.5 GB
Quick answer

A.X 3.1 needs about 24.6 GB of memory at Q4_K_M (a 22.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 22.5 GB (Q4_K_M) to 69.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

A.X 3.1 is a 34.7B-parameter model in GGUF format, quantized by jaesang-lee. Its trained context length is 32K tokens. The repository has 2 quant files, from 22.5 GB (Q4_K_M) to 69.3 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M22.5 GB 24.6 GB
Too big Get file →
BF1669.3 GB (2 parts) 71.5 GB
Too big Get file →

What GPU do you need for A.X 3.1?

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: the best quant that fits is Q4_K_M (22.5 GB file, about 24.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (22.5 GB file, about 24.6 GB in use).

Which A.X 3.1 quant should you choose?

Q4_K_M is the usual starting point for A.X 3.1: it balances file size and quality well. Here it is a 22.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters34.7B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byjaesang-lee
Base modelskt/A.X-3.1
Licenseapache-2.0
Downloads (HF)24
Last updated2026-04-06

Frequently asked questions about A.X 3.1

How much VRAM does A.X 3.1 need?

About 24.6 GB at Q4_K_M with an 8K context window. That is the 22.5 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 A.X 3.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of A.X 3.1 GGUF?

It depends on the quant: Q4_K_M is 22.5 GB, BF16 is 69.3 GB.

What context length does A.X 3.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 A.X 3.1 GGUF?

The files are on Hugging Face in the jaesang-lee/A.X-3.1-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 A.X 3.1 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.

Other GGUFs of A.X-3.1

Similar models

Browse all →

More from jaesang-lee

All by jaesang-lee →

Other large models

All large models →