BigAurelian v0.5 120b 32k i1 needs about 41.8 GB of memory at IQ2_S (a 36.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 25.0 GB (IQ1_S) to 48.3 GB (IQ3_XS).
BigAurelian v0.5 120b 32k i1 – a 120‑billion‑parameter Llama model
BigAurelian v0.5 120b 32k i1 is a 120‑billion‑parameter Llama model with a 4096‑token context window. It is a frankenmerge of aurelian‑v0.5‑70b‑32K and WinterGoddess‑1.4x‑70b, aiming for extended context performance. The model requires a compress_pos_emb factor of 8 when loading.
Good at
- Large‑scale text generation
- Long‑form content with 4096‑token context
- High‑parameter density for detailed responses
Limits
- Context limited to 4096 tokens
- No vision or multimodal support
- License: llama2
Best for
- Research prototypes needing 120b parameters
- Enterprise chatbots with long context
- Academic experiments on large LLMs
Who it’s for. Developers and researchers who need a high‑parameter Llama model with a 4096‑token context window and are comfortable managing GGUF files and custom positional embedding compression. The model is suitable for environments where GPU memory can accommodate the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 25.0 GB | 27.8 GB | Too big | Get file → | |
| IQ1_M | 27.1 GB | 29.9 GB | Too big | Get file → | |
| IQ2_XXS | 31.5 GB | 34.3 GB | Too big | Get file → | |
| IQ2_XS | 35.0 GB | 37.8 GB | Too big | Get file → | |
| IQ2_S | 36.7 GB | 39.5 GB | Too big | Get file → | |
| IQ2_M | 39.9 GB | 42.7 GB | Too big | Get file → | |
| Q2_K | 43.6 GB | 46.4 GB | Too big | Get file → | |
| IQ3_XXS | 45.5 GB | 48.3 GB | Too big | Get file → | |
| IQ3_XS | 48.3 GB | 51.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (25.04 GB file, ~30.1 GB memory at 8k context). For 12 GB VRAM, IQ1_M (27.11 GB file, ~32.2 GB memory). For 16 GB VRAM, IQ2_XXS (31.47 GB file, ~36.6 GB memory). Memory estimates are approximate.
What GPU do you need for BigAurelian v0.5 120b 32k i1?
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: the best quant that fits is IQ1_S (25.0 GB file, about 30.1 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (39.9 GB file, about 45.0 GB in use).
Which BigAurelian v0.5 120b 32k i1 quant should you choose?
IQ2_S (36.7 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 25.0 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 BigAurelian v0.5 120b 32k i1
How much VRAM does BigAurelian v0.5 120b 32k i1 need?
About 41.8 GB at IQ2_S with an 8K context window. That is the 36.7 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 BigAurelian v0.5 120b 32k i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 30.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of BigAurelian v0.5 120b 32k i1 GGUF?
It depends on the quant: IQ1_S is 25.0 GB, IQ1_M is 27.1 GB, IQ2_XXS is 31.5 GB, IQ2_XS is 35.0 GB, IQ2_S is 36.7 GB, IQ2_M is 39.9 GB and 3 more.
What context length does BigAurelian v0.5 120b 32k i1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.6 GB at 8K and 2.3 GB at 4K.
Where can I download BigAurelian v0.5 120b 32k i1 GGUF?
The files are on Hugging Face in the mradermacher/BigAurelian-v0.5-120b-32k-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 BigAurelian v0.5 120b 32k i1 use?
Hugging Face lists the license as llama2. 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 BigAurelian v0.5 120b 32k i1 on 8 GB VRAM?
Use the IQ1_S quant, which requires about 30.1 GB of VRAM at 8k context. 8 GB VRAM is insufficient.
Does this model support vision or multimodal inputs?
No, the model is purely text‑based and has no vision support.
What context length can I use with this model?
The trained context length is 4096 tokens; larger contexts are not supported.