FusionNet_7Bx2_MoE_14B needs about 9.4 GB of memory at Q4_K_M (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.8 GB (Q2_K) to 13.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
FusionNet 7Bx2 MoE 12.9B Llama model in GGUF format
FusionNet_7Bx2_MoE_14B is a 12.9B parameter Llama model fine‑tuned on English with a mixture of experts. It supports a 32768 token context window and is released under the MIT license.
Good at
- Large context handling
- Mixture of experts for specialized inference
- Compact GGUF quantizations
Limits
- No vision support
- Requires 8k context for memory estimates
- No explicit language support list
Best for
- Chatbots needing long context
- Research on MoE architectures
- Low‑latency inference on GPUs
Who it’s for. Developers and researchers who need a 12.9B Llama model with MoE capabilities and want to run it locally using GGUF and llama.cpp. The model is suitable for experimentation and deployment on systems with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 6.3 GB | Fits | Get file → | |
| IQ3_XS | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q3_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| IQ3_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| IQ3_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_M | 6.2 GB | 7.8 GB | Tight | Get file → | |
| Q3_K_L | 6.7 GB | 8.3 GB | Too big | Get file → | |
| IQ4_XS | 7.0 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_S | 7.3 GB | 8.9 GB | Too big | Get file → | |
| Q4_K_M | 7.8 GB | 9.4 GB | Too big | Get file → | |
| Q5_K_S | 8.9 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_M | 9.1 GB | 10.7 GB | Too big | Get file → | |
| Q6_K | 10.6 GB | 12.1 GB | Too big | Get file → | |
| Q8_0 | 13.7 GB | 15.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 4.76 GB, estimated 6.3 GB memory). For 12 GB VRAM, Q4_K_M (file size 7.78 GB, estimated 9.4 GB memory) or Q5_K_S (file size 8.87 GB, estimated 10.4 GB memory). For 16 GB VRAM, Q6_K (file size 10.57 GB, estimated 12.1 GB memory) or Q8_0 (file size 13.69 GB, estimated 15.3 GB memory).
What GPU do you need for FusionNet_7Bx2_MoE_14B?
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 Q3_K_M (6.2 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (9.1 GB file, about 10.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).
Which FusionNet_7Bx2_MoE_14B quant should you choose?
Q4_K_M is the usual starting point for FusionNet_7Bx2_MoE_14B: it balances file size and quality well. Here it is a 7.8 GB file.
The Q8_0 file is 13.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 4.8 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 FusionNet_7Bx2_MoE_14B
How much VRAM does FusionNet_7Bx2_MoE_14B need?
About 9.4 GB at Q4_K_M with an 8K context window. That is the 7.8 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 FusionNet_7Bx2_MoE_14B on an 8 GB GPU?
Yes, with Q3_K_M: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FusionNet_7Bx2_MoE_14B GGUF?
It depends on the quant: Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q3_K_S is 5.6 GB, IQ3_S is 5.6 GB, IQ3_M is 5.7 GB, Q3_K_M is 6.2 GB and 8 more.
What context length does FusionNet_7Bx2_MoE_14B 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 FusionNet_7Bx2_MoE_14B GGUF?
The files are on Hugging Face in the mradermacher/FusionNet_7Bx2_MoE_14B-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 FusionNet_7Bx2_MoE_14B use?
Hugging Face lists the license as mit. 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 Q2_K quant uses about 6.3 GB of VRAM at 8k context, which fits within 8 GB.
Does this model support image inputs?
No, the model has no vision capabilities and is trained only on text.
What license does the model use?
The model is released under the MIT license, allowing free use and modification.