MoE Girl 800MA 3BT needs about 3.1 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.3 GB (Q2_K) to 6.8 GB (F16).
MoE Girl 800MA 3BT – a roleplay‑centric 3.37B parameter model
MoE Girl 800MA 3BT is a 3.37B parameter model based on Granite 3.0 3B‑A800M. It is a mixture of experts fine‑tuned for roleplay. The model supports a 8192 token context window and is released under the apache‑2.0 license.
Good at
- Roleplay scenarios
- ChatML prompting
- Granite 3.0 base abilities
Limits
- 800 million active parameters
- No vision support
- Requires 8192 token context
Best for
- Chatbot roleplay
- Interactive storytelling
- Character dialogue generation
Who it’s for. Developers and hobbyists looking for a lightweight roleplay model. The model is suitable for local deployment with GGUF support and can be used with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.3 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.5 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 2.8 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_S | 2.3 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 3.4 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q8_0 | 3.6 GB | 4.6 GB | Fits | Get file → | |
| F16 | 6.8 GB | 7.8 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (2.06 GB file, ~3.1 GB VRAM). For 4 GB VRAM, use Q3_K_S (1.49 GB file, ~2.5 GB VRAM). For 2 GB VRAM, use Q2_K (1.27 GB file, ~2.3 GB VRAM).
What GPU do you need for MoE Girl 800MA 3BT?
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: the best quant that fits is Q6_K (2.8 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.8 GB file, about 7.8 GB in use).
Which MoE Girl 800MA 3BT quant should you choose?
Q4_K_M is the usual starting point for MoE Girl 800MA 3BT: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.6 GB, about 1.7 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 1.3 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 MoE Girl 800MA 3BT
How much VRAM does MoE Girl 800MA 3BT need?
About 3.1 GB at Q4_K_M with an 8K context window. That is the 2.1 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 MoE Girl 800MA 3BT on an 8 GB GPU?
Yes, with F16: the 6.8 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 MoE Girl 800MA 3BT GGUF?
It depends on the quant: Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.8 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.9 GB and 6 more.
What context length does MoE Girl 800MA 3BT 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 MoE Girl 800MA 3BT GGUF?
The files are on Hugging Face in the mradermacher/MoE-Girl-800MA-3BT-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 MoE Girl 800MA 3BT 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 MoE Girl 800MA 3BT on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 3.1 GB VRAM at 8192 context, which fits in 8 GB.
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.