Undi95 Nethena MLewd Xwin 23B needs about 0.9 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.0 GB (Q6_K) to 16.2 GB (Q5_1).
Undi95 Nethena MLewd Xwin 23B is a 23B-parameter Undi model in GGUF format, quantized by RichardErkhov. The repository has 22 quant files, from 0.0 GB (Q6_K) to 16.2 GB (Q5_1).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_M | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 1.1 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q4_K | 3.0 GB | 3.8 GB | Fits | Get file → | |
| IQ3_S | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q5_K_M | 3.9 GB | 4.9 GB | Fits | Get file → | |
| IQ3_M | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XS | 5.3 GB | 6.4 GB | Fits | Get file → | |
| Q2_K | 8.5 GB | 10.0 GB | Too big | Get file → | |
| IQ4_NL | 9.1 GB | 10.7 GB | Too big | Get file → | |
| Q3_K_S | 9.9 GB | 11.6 GB | Too big | Get file → | |
| Q3_K | 11.1 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_M | 11.1 GB | 12.9 GB | Too big | Get file → | |
| Q4_0 | 11.7 GB | 13.6 GB | Too big | Get file → | |
| Q3_K_L | 12.1 GB | 14.1 GB | Too big | Get file → | |
| IQ4_XS | 12.3 GB | 14.3 GB | Too big | Get file → | |
| Q4_K_S | 13.0 GB | 15.0 GB | Too big | Get file → | |
| Q5_0 | 15.7 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_S | 15.7 GB | 18.1 GB | Too big | Get file → | |
| Q5_K | 16.2 GB | 18.6 GB | Too big | Get file → | |
| Q5_1 | 16.2 GB | 18.6 GB | Too big | Get file → |
What GPU do you need for Undi95 Nethena MLewd Xwin 23B?
These figures add the file size, an fp16 KV cache at an 8K context window 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 Q4_K (3.0 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (4.1 GB file, about 5.1 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XS (5.3 GB file, about 6.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_S (9.9 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (13.0 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_1 (16.2 GB file, about 18.6 GB in use).
Which Undi95 Nethena MLewd Xwin 23B quant should you choose?
Q4_K_M is the usual starting point for Undi95 Nethena MLewd Xwin 23B: it balances file size and quality well. Here it is a 0.4 GB file.
The Q8_0 file is 0.6 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q6_K at 0.0 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Undi95 Nethena MLewd Xwin 23B
How much VRAM does Undi95 Nethena MLewd Xwin 23B need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.4 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 Undi95 Nethena MLewd Xwin 23B on an 8 GB GPU?
Yes, with IQ3_XS: the 5.3 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Undi95 Nethena MLewd Xwin 23B GGUF?
It depends on the quant: Q6_K is 0.0 GB, Q4_K_M is 0.4 GB, Q8_0 is 0.6 GB, Q4_1 is 2.6 GB, Q4_K is 3.0 GB, IQ3_S is 3.6 GB and 16 more.
Where can I download Undi95 Nethena MLewd Xwin 23B GGUF?
The files are on Hugging Face in the RichardErkhov/Undi95_-_Nethena-MLewd-Xwin-23B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.