BigWeave v20 110b needs about 45.2 GB of memory at Q2_K (a 40.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 8 quants, from 2.1 GB (Q3_K_L) to 49.2 GB (IQ3_M).
BigWeave v20 110b is a 110B-parameter Bigweave model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 8 quant files, from 2.1 GB (Q3_K_L) to 49.2 GB (IQ3_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 2.1 GB | 4.7 GB | Fits | Get file → | |
| Q3_K | 22.1 GB | 24.8 GB | Too big | Get file → | |
| Q3_K_M | 27.6 GB | 30.2 GB | Too big | Get file → | |
| Q2_K | 40.4 GB (2 parts) | 43.1 GB | Too big | Get file → | |
| IQ3_XS | 45.0 GB (2 parts) | 47.6 GB | Too big | Get file → | |
| Q3_K_S | 47.4 GB (2 parts) | 50.0 GB | Too big | Get file → | |
| IQ3_S | 47.5 GB (2 parts) | 50.2 GB | Too big | Get file → | |
| IQ3_M | 49.2 GB (2 parts) | 51.8 GB | Too big | Get file → |
What GPU do you need for BigWeave v20 110b?
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: the best quant that fits is Q3_K_L (2.1 GB file, about 6.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_L (2.1 GB file, about 6.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_L (2.1 GB file, about 6.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_L (2.1 GB file, about 6.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q3_K (22.1 GB file, about 26.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q2_K (40.4 GB file, about 45.2 GB in use).
Which BigWeave v20 110b quant should you choose?
Q2_K (40.4 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is Q3_K_L at 2.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about BigWeave v20 110b
How much VRAM does BigWeave v20 110b need?
About 45.2 GB at Q2_K with an 8K context window. That is the 40.4 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 v20 110b on an 8 GB GPU?
Yes, with Q3_K_L: the 2.1 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of BigWeave v20 110b GGUF?
It depends on the quant: Q3_K_L is 2.1 GB, Q3_K is 22.1 GB, Q3_K_M is 27.6 GB, Q2_K is 40.4 GB, IQ3_XS is 45.0 GB, Q3_K_S is 47.4 GB and 2 more.
What context length does BigWeave v20 110b support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download BigWeave v20 110b GGUF?
The files are on Hugging Face in the RichardErkhov/llmixer_-_BigWeave-v20-110b-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 v20 110b 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.