A.X 3.1 i1 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 24 quants, from 0.0 GB to 30.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
A.X 3.1 i1 – 34.7B Korean‑centric LLM in GGUF format
A.X 3.1 i1 is a 34.7B parameter LLM optimized for Korean language understanding. It supports 32,768 token context natively and is available in multiple GGUF quantizations. The model is licensed under Apache‑2.0.
Good at
- Korean language reasoning
- Tool usage
- Long‑context handling
Limits
- No vision support
- Requires 32,768 token context
- No mixed‑expert architecture
Best for
- Enterprise Korean NLP
- Chatbot development
- Document summarization
Who it’s for. Developers building Korean‑focused applications who need a large, efficient LLM. The model is suitable for on‑premise deployment due to its open license and GGUF format.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.1 GB | Fits | Get file → | |
| IQ1_S | 10.8 GB | 12.9 GB | Too big | Get file → | |
| IQ1_M | 11.3 GB | 13.4 GB | Too big | Get file → | |
| IQ2_XXS | 12.1 GB | 14.2 GB | Too big | Get file → | |
| IQ2_XS | 12.9 GB | 15.0 GB | Too big | Get file → | |
| IQ2_S | 13.4 GB | 15.5 GB | Too big | Get file → | |
| Q2_K_S | 14.0 GB | 16.1 GB | Too big | Get file → | |
| IQ2_M | 14.0 GB | 16.2 GB | Too big | Get file → | |
| Q2_K | 14.2 GB | 16.3 GB | Too big | Get file → | |
| IQ3_XXS | 15.1 GB | 17.2 GB | Too big | Get file → | |
| IQ3_XS | 15.7 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_S | 16.4 GB | 18.5 GB | Too big | Get file → | |
| IQ3_S | 16.4 GB | 18.5 GB | Too big | Get file → | |
| IQ3_M | 17.0 GB | 19.1 GB | Too big | Get file → | |
| Q3_K_M | 18.0 GB | 20.1 GB | Too big | Get file → | |
| Q3_K_L | 18.9 GB | 21.0 GB | Too big | Get file → | |
| IQ4_XS | 19.0 GB | 21.1 GB | Too big | Get file → | |
| Q4_0 | 19.8 GB | 21.9 GB | Too big | Get file → | |
| Q4_K_S | 20.9 GB | 23.0 GB | Too big | Get file → | |
| Q4_1 | 21.8 GB | 24.0 GB | Too big | Get file → | |
| Q4_K_M | 22.5 GB | 24.6 GB | Too big | Get file → | |
| Q5_K_S | 24.5 GB | 26.6 GB | Too big | Get file → | |
| Q5_K_M | 25.9 GB | 28.0 GB | Too big | Get file → | |
| Q6_K | 30.5 GB | 32.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (10.8 GB, 12.9 GB memory at 8 k context). For 12 GB VRAM, IQ2_S (12.85 GB, 15 GB memory). For 16 GB VRAM, Q2_K (14.23 GB, 16.3 GB memory). Larger VRAM allows higher‑quality quants such as Q4_K_M (22.46 GB, 24.6 GB memory).
What GPU do you need for A.X 3.1 i1?
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 the main file (0.0 GB file, about 2.1 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_S (13.4 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (21.8 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (25.9 GB file, about 28.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (30.5 GB file, about 32.6 GB in use).
Which A.X 3.1 i1 quant should you choose?
Q4_K_M is the usual starting point for A.X 3.1 i1: it balances file size and quality well. Here it is a 22.5 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 A.X 3.1 i1
How much VRAM does A.X 3.1 i1 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 i1 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 A.X 3.1 i1 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 10.8 GB, IQ1_M is 11.3 GB, IQ2_XXS is 12.1 GB, IQ2_XS is 12.9 GB, IQ2_S is 13.4 GB and 18 more.
What context length does A.X 3.1 i1 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 i1 GGUF?
The files are on Hugging Face in the mradermacher/A.X-3.1-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 A.X 3.1 i1 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 A.X 3.1 i1 on 8 GB VRAM?
Yes, the IQ1_S quant uses 10.8 GB file size and requires about 12.9 GB memory at 8 k context, which fits 8 GB VRAM with off‑load or swap.
Does the model support vision tasks?
No, the model has no vision capabilities.
What context length does it support?
It supports up to 32,768 tokens natively and up to 131,072 tokens with YaRN.