Anubis Pro 105B V1A needs about 67.5 GB of memory at Q4_K_M (a 63.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 38.8 GB (Q2_K) to 111.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 16.1 GB.
Anubis Pro 105B V1A is a 105B-parameter Anubis model in GGUF format, quantized by TheDrummer. Its trained context length is 128K tokens. The repository has 6 quant files, from 38.8 GB (Q2_K) to 111.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 38.8 GB | 43.4 GB | Too big | Get file → | |
| Q3_K_M | 50.6 GB (2 parts) | 55.1 GB | Too big | Get file → | |
| Q4_K_M | 63.0 GB (2 parts) | 67.5 GB | Too big | Get file → | |
| Q5_K_M | 74.1 GB (2 parts) | 78.7 GB | Too big | Get file → | |
| Q6_K | 86.0 GB (2 parts) | 90.5 GB | Too big | Get file → | |
| Q8_0 | 111.3 GB (3 parts) | 115.9 GB | Too big | Get file → |
What GPU do you need for Anubis Pro 105B V1A?
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 (38.8 GB file, about 43.4 GB in use).
Which Anubis Pro 105B V1A quant should you choose?
Q4_K_M is the usual starting point for Anubis Pro 105B V1A: it balances file size and quality well. Here it is a 63.0 GB file.
The Q8_0 file is 111.3 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 Q2_K at 38.8 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 Anubis Pro 105B V1A
How much VRAM does Anubis Pro 105B V1A need?
About 67.5 GB at Q4_K_M with an 8K context window. That is the 63.0 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 Anubis Pro 105B V1A on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 43.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Anubis Pro 105B V1A GGUF?
It depends on the quant: Q2_K is 38.8 GB, Q3_K_M is 50.6 GB, Q4_K_M is 63.0 GB, Q5_K_M is 74.1 GB, Q6_K is 86.0 GB, Q8_0 is 111.3 GB.
What context length does Anubis Pro 105B V1A support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.0 GB at 8K and 16.1 GB at 32K.
Where can I download Anubis Pro 105B V1A GGUF?
The files are on Hugging Face in the TheDrummer/Anubis-Pro-105B-v1-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 Anubis Pro 105B V1A use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.