Aurora-10.7B needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 2.4 GB (IQ1_S) to 8.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Aurora-10.7B: 10.7B llama model with 32k context
Aurora-10.7B is a 10.7B parameter llama model with a 32768 token context window. It is available in multiple GGUF quantizations ranging from IQ1_S to Q6_K. The model is licensed under apache-2.0 and has no vision support.
Good at
- Large context generation
- Low‑memory inference
- Open‑source compatibility
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Chatbot back‑ends
- Research prototyping
- Embedded inference
Who it’s for. Developers and researchers who need a large‑context llama model that can run on consumer GPUs. The model is suitable for applications that can tolerate the lack of vision capabilities and require an open‑source license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.4 GB | 4.5 GB | Fits | Get file → | |
| IQ1_M | 2.6 GB | 4.7 GB | Fits | Get file → | |
| IQ2_XXS | 2.9 GB | 5.0 GB | Fits | Get file → | |
| IQ2_XS | 3.2 GB | 5.3 GB | Fits | Get file → | |
| IQ2_S | 3.4 GB | 5.5 GB | Fits | Get file → | |
| IQ2_M | 3.7 GB | 5.8 GB | Fits | Get file → | |
| Q2_K | 4.0 GB | 6.1 GB | Fits | Get file → | |
| IQ3_XXS | 4.2 GB | 6.3 GB | Fits | Get file → | |
| IQ3_XS | 4.4 GB | 6.6 GB | Fits | Get file → | |
| Q3_K_S | 4.7 GB | 6.8 GB | Fits | Get file → | |
| IQ3_S | 4.7 GB | 6.8 GB | Fits | Get file → | |
| IQ3_M | 4.8 GB | 7.0 GB | Fits | Get file → | |
| Q3_K_M | 5.2 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_L | 5.7 GB | 7.8 GB | Tight | Get file → | |
| IQ4_XS | 5.8 GB | 7.9 GB | Tight | Get file → | |
| Q4_0 | 6.1 GB | 8.2 GB | Too big | Get file → | |
| Q4_K_S | 6.1 GB | 8.2 GB | Too big | Get file → | |
| Q4_K_M | 6.5 GB | 8.6 GB | Too big | Get file → | |
| Q5_K_S | 7.4 GB | 9.5 GB | Too big | Get file → | |
| Q5_K_M | 7.6 GB | 9.7 GB | Too big | Get file → | |
| Q6_K | 8.8 GB | 10.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.35 GB file, 4.5 GB memory) or IQ1_M (2.56 GB file, 4.7 GB memory). For 12 GB VRAM, Q4_K_M (6.46 GB file, 8.6 GB memory) or Q5_K_M (7.6 GB file, 9.7 GB memory) are suitable. Higher‑quality quants like Q6_K require 8.81 GB file and 10.9 GB memory, suitable for 16 GB VRAM setups.
What GPU do you need for Aurora-10.7B?
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 IQ2_M (3.7 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ4_XS (5.8 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
Which Aurora-10.7B quant should you choose?
Q4_K_M is the usual starting point for Aurora-10.7B: it balances file size and quality well. Here it is a 6.5 GB file.
If memory is tight, the smallest file is IQ1_S at 2.4 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 Aurora-10.7B
How much VRAM does Aurora-10.7B need?
About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 Aurora-10.7B on an 8 GB GPU?
Yes, with IQ4_XS: the 5.8 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Aurora-10.7B GGUF?
It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.6 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.2 GB, IQ2_S is 3.4 GB, IQ2_M is 3.7 GB and 15 more.
What context length does Aurora-10.7B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Aurora-10.7B GGUF?
The files are on Hugging Face in the mradermacher/Aurora-10.7B-i1-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 Aurora-10.7B 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.
Can I run Aurora-10.7B on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM with estimated memory usage of 4.5–4.7 GB at 8k context.
Does Aurora-10.7B support vision tasks?
No, the model has no vision capabilities.
What license applies to Aurora-10.7B?
The model is released under the apache-2.0 license.