NaruMOE-3x7B-v2 needs about 12.8 GB of memory at Q4_K_M (a 11.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 3.9 GB (IQ1_S) to 15.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
18.5B parameter NaruMOE-3x7B-v2 with 32k context
NaruMOE-3x7B-v2 is a 18.5B parameter mixture of experts model based on the llama architecture. It supports a 32768 token context window and is available in multiple GGUF quantizations. The model is licensed under cc‑by‑nc‑4.0.
Good at
- Roleplay scenarios
- Large context handling
- Mixture‑of‑experts inference
Limits
- No vision support
- CC‑BY‑NC license restricts commercial use
- Requires 8k context for memory estimates
Best for
- Chatbots needing long context
- Interactive storytelling
- Role‑based dialogue systems
Who it’s for. Developers building conversational agents that need extended context and can work within a non‑commercial license. The model is suitable for research and hobby projects that require roleplay capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ1_M | 4.3 GB | 5.8 GB | Fits | Get file → | |
| IQ2_XXS | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ2_XS | 5.5 GB | 7.1 GB | Fits | Get file → | |
| IQ2_S | 5.6 GB | 7.2 GB | Tight | Get file → | |
| IQ2_M | 6.2 GB | 7.7 GB | Tight | Get file → | |
| Q2_K | 6.8 GB | 8.4 GB | Too big | Get file → | |
| IQ3_XXS | 7.1 GB | 8.7 GB | Too big | Get file → | |
| IQ3_XS | 7.6 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_S | 8.0 GB | 9.6 GB | Too big | Get file → | |
| IQ3_S | 8.0 GB | 9.6 GB | Too big | Get file → | |
| IQ3_M | 8.2 GB | 9.8 GB | Too big | Get file → | |
| Q3_K_M | 8.9 GB | 10.5 GB | Too big | Get file → | |
| Q3_K_L | 9.6 GB | 11.2 GB | Too big | Get file → | |
| IQ4_XS | 9.9 GB | 11.5 GB | Too big | Get file → | |
| Q4_0 | 10.5 GB | 12.1 GB | Too big | Get file → | |
| Q4_K_S | 10.5 GB | 12.1 GB | Too big | Get file → | |
| Q4_K_M | 11.2 GB | 12.8 GB | Too big | Get file → | |
| Q5_K_S | 12.8 GB | 14.3 GB | Too big | Get file → | |
| Q5_K_M | 13.1 GB | 14.7 GB | Too big | Get file → | |
| Q6_K | 15.2 GB | 16.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 3.88 GB, estimated memory 5.5 GB). With 12 GB VRAM, IQ4_K_S (10.54 GB, 12.1 GB). For 16 GB VRAM, Q6_K (15.19 GB, 16.8 GB). Estimates are approximate.
What GPU do you need for NaruMOE-3x7B-v2?
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 IQ1_M (4.3 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ2_M (6.2 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (9.9 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (13.1 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (15.2 GB file, about 16.8 GB in use).
Which NaruMOE-3x7B-v2 quant should you choose?
Q4_K_M is the usual starting point for NaruMOE-3x7B-v2: it balances file size and quality well. Here it is a 11.2 GB file.
If memory is tight, the smallest file is IQ1_S at 3.9 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 NaruMOE-3x7B-v2
How much VRAM does NaruMOE-3x7B-v2 need?
About 12.8 GB at Q4_K_M with an 8K context window. That is the 11.2 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 NaruMOE-3x7B-v2 on an 8 GB GPU?
Yes, with IQ2_M: the 6.2 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NaruMOE-3x7B-v2 GGUF?
It depends on the quant: IQ1_S is 3.9 GB, IQ1_M is 4.3 GB, IQ2_XXS is 4.9 GB, IQ2_XS is 5.5 GB, IQ2_S is 5.6 GB, IQ2_M is 6.2 GB and 15 more.
What context length does NaruMOE-3x7B-v2 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 NaruMOE-3x7B-v2 GGUF?
The files are on Hugging Face in the mradermacher/NaruMOE-3x7B-v2-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 NaruMOE-3x7B-v2 use?
Hugging Face lists the license as cc-by-nc-4.0. 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 NaruMOE-3x7B-v2 on 8 GB VRAM?
Yes, the IQ1_S quant uses about 5.5 GB of VRAM at 8k context, fitting within an 8 GB budget.
Does this model support image input?
No, the model has no vision capabilities.
Is the model free for commercial use?
No, it is licensed under cc‑by‑nc‑4.0, which prohibits commercial use.