A.X 4.0 bf16 needs about 147.0 GB of memory at BF16 (a 143.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
A.X 4.0 bf16 is a 71.9B-parameter Hojun model in GGUF format, quantized by hojun1229. Its trained context length is 128K tokens. The repository has 1 quant file, from 143.8 GB (BF16) to 143.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 143.8 GB | 147.0 GB | Too big | Get file → |
What GPU do you need for A.X 4.0 bf16?
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: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which A.X 4.0 bf16 quant should you choose?
BF16 (143.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about A.X 4.0 bf16
How much VRAM does A.X 4.0 bf16 need?
About 147.0 GB at BF16 with an 8K context window. That is the 143.8 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 bf16 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 147.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of A.X 4.0 bf16 GGUF?
It depends on the quant: BF16 is 143.8 GB.
What context length does A.X 4.0 bf16 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 bf16 GGUF?
The files are on Hugging Face in the hojun1229/A.X-4.0-bf16-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 4.0 bf16 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.