BigWeave v18 108b needs about 51.7 GB of memory at Q3_K_S (a 47.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 40.1 GB (Q2_K) to 48.7 GB (IQ3_M).
BigWeave v18 108b is a 108B-parameter Bigweave model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 5 quant files, from 40.1 GB (Q2_K) to 48.7 GB (IQ3_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 40.1 GB | 44.8 GB | Too big | Get file → | |
| IQ3_XS | 44.4 GB | 49.2 GB | Too big | Get file → | |
| Q3_K_S | 47.0 GB | 51.7 GB | Too big | Get file → | |
| IQ3_S | 47.1 GB | 51.8 GB | Too big | Get file → | |
| IQ3_M | 48.7 GB | 53.4 GB | Too big | Get file → |
What GPU do you need for BigWeave v18 108b?
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: the best quant that fits is Q2_K (40.1 GB file, about 44.8 GB in use).
Which BigWeave v18 108b quant should you choose?
Q3_K_S (47.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 40.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about BigWeave v18 108b
How much VRAM does BigWeave v18 108b need?
About 51.7 GB at Q3_K_S with an 8K context window. That is the 47.0 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 BigWeave v18 108b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 44.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of BigWeave v18 108b GGUF?
It depends on the quant: Q2_K is 40.1 GB, IQ3_XS is 44.4 GB, Q3_K_S is 47.0 GB, IQ3_S is 47.1 GB, IQ3_M is 48.7 GB.
What context length does BigWeave v18 108b support?
The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.9 GB at 32K.
Where can I download BigWeave v18 108b GGUF?
The files are on Hugging Face in the mradermacher/BigWeave-v18-108b-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 BigWeave v18 108b use?
Hugging Face lists the license as unknown. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.