Undi95 UndiMix v3 13B needs about 4.2 GB of memory at Q4_K_M (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 19 quants, from 1.0 GB (Q4_1) to 13.8 GB (Q8_0).
Undi95 UndiMix v3 13B is a 13B-parameter Undi model in GGUF format, quantized by RichardErkhov. The repository has 19 quant files, from 1.0 GB (Q4_1) to 13.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_1 | 1.0 GB | 1.6 GB | Fits | Get file → | |
| IQ4_NL | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q4_K_M | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 4.1 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_L | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q2_K | 4.9 GB | 5.9 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_S | 5.7 GB | 6.8 GB | Fits | Get file → | |
| IQ4_XS | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q3_K | 6.3 GB | 7.6 GB | Tight | Get file → | |
| Q3_K_M | 6.3 GB | 7.6 GB | Tight | Get file → | |
| Q4_0 | 7.4 GB | 8.7 GB | Too big | Get file → | |
| Q5_0 | 7.5 GB | 9.0 GB | Too big | Get file → | |
| Q4_K | 7.9 GB | 9.3 GB | Too big | Get file → | |
| Q5_K | 9.2 GB | 10.8 GB | Too big | Get file → | |
| Q5_K_M | 9.2 GB | 10.8 GB | Too big | Get file → | |
| Q5_1 | 9.8 GB | 11.4 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 12.5 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 16.0 GB | Too big | Get file → |
What GPU do you need for Undi95 UndiMix v3 13B?
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 IQ4_NL (2.9 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q2_K (4.9 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K (6.3 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_1 (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 16.0 GB in use).
Which Undi95 UndiMix v3 13B quant should you choose?
Q4_K_M is the usual starting point for Undi95 UndiMix v3 13B: it balances file size and quality well. Here it is a 3.3 GB file.
The Q8_0 file is 13.8 GB, about 4.2 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 Q4_1 at 1.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Undi95 UndiMix v3 13B
How much VRAM does Undi95 UndiMix v3 13B need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 3.3 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 Undi95 UndiMix v3 13B on an 8 GB GPU?
Yes, with Q3_K: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Undi95 UndiMix v3 13B GGUF?
It depends on the quant: Q4_1 is 1.0 GB, IQ4_NL is 2.9 GB, Q4_K_M is 3.3 GB, Q4_K_S is 4.1 GB, Q3_K_L is 4.1 GB, Q2_K is 4.9 GB and 13 more.
Where can I download Undi95 UndiMix v3 13B GGUF?
The files are on Hugging Face in the RichardErkhov/Undi95_-_UndiMix-v3-13B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.