Grafted Wind Elementals 2x70B i1 needs about 40.3 GB of memory at IQ2_XS (a 37.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 8 quants, from 26.2 GB (IQ1_S) to 48.5 GB (IQ3_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Grafted Wind Elementals 2x70B i1 – a 125B MoE Llama model
Grafted Wind Elementals 2x70B i1 is a 125B parameter Llama model with a mixture of experts. It was trained on 32768 context tokens and is available in several GGUF quantizations. The model is licensed for non‑commercial research use only.
Good at
- Large context generation
- Mixture of experts handling
- High‑capacity language modeling
Limits
- Non‑commercial license
- No vision support
- Requires large VRAM for full precision
Best for
- Research prototyping
- Long‑form content creation
- Academic experimentation
Who it’s for. Researchers and developers needing a large‑scale Llama model for non‑commercial projects. The model is suitable for those who can manage the memory demands and comply with the license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 26.2 GB | 29.4 GB | Too big | Get file → | |
| IQ1_M | 28.3 GB | 31.5 GB | Too big | Get file → | |
| IQ2_XXS | 33.3 GB | 36.5 GB | Too big | Get file → | |
| IQ2_XS | 37.1 GB | 40.3 GB | Too big | Get file → | |
| IQ2_S | 38.3 GB | 41.5 GB | Too big | Get file → | |
| IQ2_M | 41.9 GB | 45.1 GB | Too big | Get file → | |
| Q2_K | 46.2 GB | 49.4 GB | Too big | Get file → | |
| IQ3_XXS | 48.5 GB | 51.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (26.2 GB file, 29.4 GB memory at 8 k context). If you have 12 GB VRAM, IQ1_M (28.28 GB file, 31.5 GB memory) is a good choice. For 16 GB VRAM, IQ2_XXS (33.33 GB file, 36.5 GB memory) provides a balance between size and performance.
What GPU do you need for Grafted Wind Elementals 2x70B 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_M (28.3 GB file, about 31.5 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (41.9 GB file, about 45.1 GB in use).
Which Grafted Wind Elementals 2x70B i1 quant should you choose?
IQ2_XS (37.1 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 26.2 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
Frequently asked questions about Grafted Wind Elementals 2x70B i1
How much VRAM does Grafted Wind Elementals 2x70B i1 need?
About 40.3 GB at IQ2_XS with an 8K context window. That is the 37.1 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 Grafted Wind Elementals 2x70B i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Grafted Wind Elementals 2x70B i1 GGUF?
It depends on the quant: IQ1_S is 26.2 GB, IQ1_M is 28.3 GB, IQ2_XXS is 33.3 GB, IQ2_XS is 37.1 GB, IQ2_S is 38.3 GB, IQ2_M is 41.9 GB and 2 more.
What context length does Grafted Wind Elementals 2x70B i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Grafted Wind Elementals 2x70B i1 GGUF?
The files are on Hugging Face in the mradermacher/Grafted-Wind-Elementals-2x70B-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 Grafted Wind Elementals 2x70B i1 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.
Can I run this model on 8 GB VRAM?
Yes, the IQ1_S quantization requires 29.4 GB memory at 8 k context, which is beyond 8 GB VRAM, so it is not feasible. You would need a higher VRAM GPU.
Is this model suitable for commercial use?
No, the license restricts use to non‑commercial research only.
Does the model support vision tasks?
No, the model has no vision capabilities.