bitnet_b1_58-large needs about 2.0 GB of memory at its main file (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB to 2.9 GB (F32).
bitnet_b1_58-large is a 729M-parameter Bitnet model in GGUF format, quantized by mardakani. Its trained context length is 2K tokens. The repository has 4 quant files, from 0.3 GB to 2.9 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 1.1 GB | Fits | Get file → | |
| — | 0.3 GB | 1.1 GB | Fits | Get file → | |
| F32 | 2.9 GB | 3.7 GB | Fits | Get file → | |
| F32 | 2.9 GB | 3.7 GB | Fits | Get file → |
What GPU do you need for bitnet_b1_58-large?
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 (0.3 GB file, about 2.0 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (2.9 GB file, about 4.6 GB in use).
Which bitnet_b1_58-large quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.3 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 bitnet_b1_58-large
How much VRAM does bitnet_b1_58-large need?
About 2.0 GB at its main file with an 8K context window. That is the 0.3 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 bitnet_b1_58-large on an 8 GB GPU?
Yes, with F32: the 2.9 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bitnet_b1_58-large GGUF?
It depends on the quant: file is 0.3 GB, file is 0.3 GB, F32 is 2.9 GB, F32 is 2.9 GB.
What context length does bitnet_b1_58-large support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.2 GB at 8K and 0.3 GB at 2K.
Where can I download bitnet_b1_58-large GGUF?
The files are on Hugging Face in the mardakani/Bitnet repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does bitnet_b1_58-large use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.