Moonlight 16B A3B Instruct needs about 11.5 GB of memory at Q4_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 5.8 GB (IQ2_XXS) to 31.9 GB (F16).
Moonlight 16B A3B Instruct – 16B Mixture‑of‑Expert instruction model
Moonlight 16B A3B Instruct is a 16B‑parameter Mixture‑of‑Expert model based on the deepseek2 architecture. It was trained with 5.7T tokens using the Muon optimizer and is instruction tuned. The model supports a 8192‑token context window and is released under the MIT license.
Good at
- Instruction following
- Large context reasoning
- Mixture‑of‑Expert scaling
Limits
- No vision support
- Requires 8k context for full capability
- Large memory footprint for higher quants
Best for
- Chatbots needing long context
- Research on MoE architectures
- Fine‑tuning instruction models
Who it’s for. Developers and researchers who need a large‑scale instruction model with a 8192‑token context. The model is suitable for environments that can accommodate its memory requirements and support the deepseek2 architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 5.8 GB | 6.8 GB | Fits | Get file → | |
| IQ2_XS | 6.1 GB | 7.1 GB | Fits | Get file → | |
| IQ2_S | 6.2 GB | 7.1 GB | Fits | Get file → | |
| IQ2_M | 6.5 GB | 7.5 GB | Tight | Get file → | |
| Q2_K | 6.6 GB | 7.6 GB | Tight | Get file → | |
| Q2_K_S | 6.6 GB | 7.6 GB | Tight | Get file → | |
| IQ3_XXS | 7.1 GB | 8.1 GB | Too big | Get file → | |
| IQ3_XS | 7.3 GB | 8.3 GB | Too big | Get file → | |
| IQ3_S | 7.6 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_S | 7.6 GB | 8.6 GB | Too big | Get file → | |
| IQ3_M | 7.7 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 8.3 GB | 9.3 GB | Too big | Get file → | |
| Q3_K_L | 8.6 GB | 9.6 GB | Too big | Get file → | |
| IQ4_XS | 8.7 GB | 9.7 GB | Too big | Get file → | |
| IQ4_NL | 9.1 GB | 10.1 GB | Too big | Get file → | |
| Q4_0 | 9.1 GB | 10.1 GB | Too big | Get file → | |
| Q4_K_S | 9.7 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_M | 10.5 GB | 11.5 GB | Too big | Get file → | |
| Q5_0 | 11.1 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_S | 11.3 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_M | 12.0 GB | 13.0 GB | Too big | Get file → | |
| Q6_K | 14.3 GB | 15.3 GB | Too big | Get file → | |
| Q8_0 | 17.0 GB | 18.0 GB | Too big | Get file → | |
| F16 | 31.9 GB | 32.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS or IQ2_XS. For 12 GB VRAM, IQ3_XS or IQ3_S are suitable. For 16 GB VRAM, Q4_K_S or Q4_K_M provide a good balance between quality and memory usage. The estimates are approximate.
What GPU do you need for Moonlight 16B A3B Instruct?
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 Q2_K_S (6.6 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_0 (11.1 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (14.3 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (17.0 GB file, about 18.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (17.0 GB file, about 18.0 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (31.9 GB file, about 32.9 GB in use).
Which Moonlight 16B A3B Instruct quant should you choose?
Q4_K_M is the usual starting point for Moonlight 16B A3B Instruct: it balances file size and quality well. Here it is a 10.5 GB file.
The Q8_0 file is 17.0 GB, about 1.6 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 IQ2_XXS at 5.8 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 Moonlight 16B A3B Instruct
How much VRAM does Moonlight 16B A3B Instruct need?
About 11.5 GB at Q4_K_M with an 8K context window. That is the 10.5 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 Moonlight 16B A3B Instruct on an 8 GB GPU?
Yes, with Q2_K_S: the 6.6 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Moonlight 16B A3B Instruct GGUF?
It depends on the quant: IQ2_XXS is 5.8 GB, IQ2_XS is 6.1 GB, IQ2_S is 6.2 GB, IQ2_M is 6.5 GB, Q2_K is 6.6 GB, Q2_K_S is 6.6 GB and 18 more.
What context length does Moonlight 16B A3B Instruct support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.5 GB at 8K.
Where can I download Moonlight 16B A3B Instruct GGUF?
The files are on Hugging Face in the gabriellarson/Moonlight-16B-A3B-Instruct-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 Moonlight 16B A3B Instruct 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 Moonlight 16B A3B Instruct on 8 GB VRAM?
Yes, using the IQ2_XXS or IQ2_XS quantizations which estimate 6.8–7.1 GB at 8k context.
Does the model support image inputs?
No, the model has no vision capabilities.
What context length does the model support?
The model was trained with 8192 tokens and performs best with that context length.