Eurus 70b Nca needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 2.0 GB (Q5_K_S) to 73.3 GB (Q8_0).
Eurus 70b Nca is a 69B-parameter Eurus model in GGUF format, quantized by RichardErkhov. Its trained context length is 16K tokens. The repository has 22 quant files, from 2.0 GB (Q5_K_S) to 73.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 2.0 GB | 5.2 GB | Fits | Get file → | |
| Q2_K | 25.5 GB | 28.6 GB | Too big | Get file → | |
| IQ3_XS | 28.3 GB | 31.5 GB | Too big | Get file → | |
| IQ3_S | 29.9 GB | 33.1 GB | Too big | Get file → | |
| Q3_K_S | 29.9 GB | 33.1 GB | Too big | Get file → | |
| IQ3_M | 30.9 GB | 34.1 GB | Too big | Get file → | |
| Q3_K | 33.3 GB | 36.5 GB | Too big | Get file → | |
| Q3_K_M | 33.3 GB | 36.5 GB | Too big | Get file → | |
| Q5_K | 35.9 GB | 39.1 GB | Too big | Get file → | |
| Q3_K_L | 36.1 GB | 39.3 GB | Too big | Get file → | |
| IQ4_XS | 37.2 GB | 40.4 GB | Too big | Get file → | |
| Q4_0 | 38.9 GB | 42.1 GB | Too big | Get file → | |
| IQ4_NL | 39.2 GB | 42.4 GB | Too big | Get file → | |
| Q4_K_S | 39.2 GB | 42.4 GB | Too big | Get file → | |
| Q4_K | 41.4 GB (2 parts) | 44.6 GB | Too big | Get file → | |
| Q4_K_M | 41.4 GB (2 parts) | 44.6 GB | Too big | Get file → | |
| Q4_1 | 43.2 GB (2 parts) | 46.4 GB | Too big | Get file → | |
| Q5_0 | 47.5 GB (2 parts) | 50.6 GB | Too big | Get file → | |
| Q5_K_M | 48.8 GB (2 parts) | 51.9 GB | Too big | Get file → | |
| Q5_1 | 51.8 GB (2 parts) | 54.9 GB | Too big | Get file → | |
| Q6_K | 56.6 GB (2 parts) | 59.8 GB | Too big | Get file → | |
| Q8_0 | 73.3 GB (2 parts) | 76.5 GB | Too big | Get file → |
What GPU do you need for Eurus 70b Nca?
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: the best quant that fits is Q5_K_S (2.0 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_S (2.0 GB file, about 5.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_S (2.0 GB file, about 5.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_S (2.0 GB file, about 5.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_S (2.0 GB file, about 5.2 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XS (28.3 GB file, about 31.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_1 (43.2 GB file, about 46.4 GB in use).
Which Eurus 70b Nca quant should you choose?
Q4_K_M is the usual starting point for Eurus 70b Nca: it balances file size and quality well. Here it is a 41.4 GB file.
The Q8_0 file is 73.3 GB, about 1.8 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 Q5_K_S at 2.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Eurus 70b Nca
How much VRAM does Eurus 70b Nca need?
About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 Eurus 70b Nca on an 8 GB GPU?
Yes, with Q5_K_S: the 2.0 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Eurus 70b Nca GGUF?
It depends on the quant: Q5_K_S is 2.0 GB, Q2_K is 25.5 GB, IQ3_XS is 28.3 GB, IQ3_S is 29.9 GB, Q3_K_S is 29.9 GB, IQ3_M is 30.9 GB and 16 more.
What context length does Eurus 70b Nca support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.7 GB at 8K and 5.4 GB at 16K.
Where can I download Eurus 70b Nca GGUF?
The files are on Hugging Face in the RichardErkhov/openbmb_-_Eurus-70b-nca-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 Eurus 70b Nca use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.