NeuralMona MoE 4x7B i1 needs about 16.3 GB of memory at Q4_K_M (a 14.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 5.2 GB (IQ1_S) to 20.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
NeuralMona MoE 4x7B i1 – a 24.2B Mixture of Experts model in GGUF format
NeuralMona MoE 4x7B i1 is a 24.2B parameter Mixture of Experts model based on the Neuralmona family. It supports a 32768 token context window and is released under the apache-2.0 license. The model is available in multiple quantized GGUF variants.
Good at
- Large context handling
- Mixture of experts for diverse tasks
- High parameter count
Limits
- No vision support
- Requires significant VRAM for larger quants
- No active parameter count specified
Best for
- Long-form content generation
- Complex reasoning tasks
- Fine-tuning with limited GPU memory
Who it’s for. Developers and researchers who need a large, context‑rich language model and can manage the memory requirements. Suitable for environments that support llama.cpp and GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 5.2 GB | 6.8 GB | Fits | Get file → | |
| IQ1_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| IQ2_XXS | 6.6 GB | 8.1 GB | Too big | Get file → | |
| IQ2_XS | 7.3 GB | 8.9 GB | Too big | Get file → | |
| IQ2_S | 7.5 GB | 9.0 GB | Too big | Get file → | |
| IQ2_M | 8.2 GB | 9.7 GB | Too big | Get file → | |
| Q2_K | 9.0 GB | 10.6 GB | Too big | Get file → | |
| IQ3_XXS | 9.5 GB | 11.0 GB | Too big | Get file → | |
| IQ3_XS | 10.0 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_S | 10.6 GB | 12.2 GB | Too big | Get file → | |
| IQ3_S | 10.6 GB | 12.2 GB | Too big | Get file → | |
| IQ3_M | 10.8 GB | 12.4 GB | Too big | Get file → | |
| Q3_K_M | 11.7 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_L | 12.7 GB | 14.3 GB | Too big | Get file → | |
| IQ4_XS | 13.0 GB | 14.6 GB | Too big | Get file → | |
| IQ4_NL | 13.8 GB | 15.4 GB | Too big | Get file → | |
| Q4_0 | 13.8 GB | 15.4 GB | Too big | Get file → | |
| Q4_K_S | 13.9 GB | 15.5 GB | Too big | Get file → | |
| Q4_K_M | 14.8 GB | 16.3 GB | Too big | Get file → | |
| Q5_K_S | 16.8 GB | 18.4 GB | Too big | Get file → | |
| Q5_K_M | 17.3 GB | 18.9 GB | Too big | Get file → | |
| Q6_K | 20.0 GB | 21.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (5.18 GB file, 6.8 GB memory) or IQ1_M (5.7 GB file, 7.3 GB memory). With 12 GB VRAM, IQ2_S (7.47 GB file, 9 GB memory) or Q2_K (9 GB file, 10.6 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q4_K_M (14.76 GB file, 16.3 GB memory).
What GPU do you need for NeuralMona MoE 4x7B 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: the best quant that fits is IQ1_M (5.7 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (10.0 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (13.9 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (20.0 GB file, about 21.5 GB in use).
Which NeuralMona MoE 4x7B i1 quant should you choose?
Q4_K_M is the usual starting point for NeuralMona MoE 4x7B i1: it balances file size and quality well. Here it is a 14.8 GB file.
If memory is tight, the smallest file is IQ1_S at 5.2 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
Source
Frequently asked questions about NeuralMona MoE 4x7B i1
How much VRAM does NeuralMona MoE 4x7B i1 need?
About 16.3 GB at Q4_K_M with an 8K context window. That is the 14.8 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 NeuralMona MoE 4x7B i1 on an 8 GB GPU?
Yes, with IQ1_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NeuralMona MoE 4x7B i1 GGUF?
It depends on the quant: IQ1_S is 5.2 GB, IQ1_M is 5.7 GB, IQ2_XXS is 6.6 GB, IQ2_XS is 7.3 GB, IQ2_S is 7.5 GB, IQ2_M is 8.2 GB and 16 more.
What context length does NeuralMona MoE 4x7B 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 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download NeuralMona MoE 4x7B i1 GGUF?
The files are on Hugging Face in the mradermacher/NeuralMona_MoE-4x7B-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 NeuralMona MoE 4x7B i1 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 NeuralMona MoE 4x7B i1 on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM, with estimated memory usage of 6.8 GB or 7.3 GB respectively.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.