NinjaMouse 2.4B 32L Danube needs about 2.6 GB of memory at Q4_K_M (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.6 GB (IQ1_S) to 2.0 GB (Q6_K).
NinjaMouse 2.4B 32L Danube – a 2.39B‑parameter Llama model
NinjaMouse 2.4B 32L Danube extends the original 24‑layer model to 32 layers. It supports coding, roleplay, and tool use. The model is released under the Apache‑2.0 license and trained with a 16,384‑token context window.
Good at
- Coding tasks
- Role‑playing scenarios
- Tool integration
Limits
- Limited to 16,384 tokens context
- No vision capabilities
- Requires Apache‑2.0 compliant usage
Best for
- Developers building lightweight LLM apps
- Educators needing a small coding assistant
- Researchers testing 32‑layer Llama variants
Who it’s for. This model is suitable for developers and researchers who need a compact Llama‑style model with extended layer depth. It is ideal for those who can run it on GPUs with at least 8 GB of VRAM and who respect the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.6 GB | 1.7 GB | Fits | Get file → | |
| IQ1_M | 0.6 GB | 1.8 GB | Fits | Get file → | |
| IQ2_XXS | 0.7 GB | 1.8 GB | Fits | Get file → | |
| IQ2_XS | 0.7 GB | 1.9 GB | Fits | Get file → | |
| IQ2_S | 0.8 GB | 2.0 GB | Fits | Get file → | |
| IQ2_M | 0.8 GB | 2.0 GB | Fits | Get file → | |
| Q2_K_S | 0.9 GB | 2.0 GB | Fits | Get file → | |
| Q2_K | 0.9 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XXS | 0.9 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XS | 1.0 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 1.1 GB | 2.2 GB | Fits | Get file → | |
| IQ3_S | 1.1 GB | 2.2 GB | Fits | Get file → | |
| IQ3_M | 1.1 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.2 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_L | 1.3 GB | 2.4 GB | Fits | Get file → | |
| IQ4_XS | 1.3 GB | 2.5 GB | Fits | Get file → | |
| Q4_0 | 1.4 GB | 2.5 GB | Fits | Get file → | |
| IQ4_NL | 1.4 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.4 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.4 GB | 2.6 GB | Fits | Get file → | |
| Q4_1 | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_S | 1.7 GB | 2.8 GB | Fits | Get file → | |
| Q5_K_M | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q6_K | 2.0 GB | 3.1 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S (0.56 GB, 1.7 GB memory) or IQ1_M (0.6 GB, 1.8 GB memory). If you have 12 GB VRAM, Q4_K_M (1.44 GB, 2.6 GB memory) offers a good balance of size and performance. Larger GPUs can handle Q5_K_M or Q6_K for higher precision.
What GPU do you need for NinjaMouse 2.4B 32L Danube?
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 (2.0 GB file, about 3.1 GB in use).
Which NinjaMouse 2.4B 32L Danube quant should you choose?
Q4_K_M is the usual starting point for NinjaMouse 2.4B 32L Danube: it balances file size and quality well. Here it is a 1.4 GB file.
If memory is tight, the smallest file is IQ1_S at 0.6 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 NinjaMouse 2.4B 32L Danube
How much VRAM does NinjaMouse 2.4B 32L Danube need?
About 2.6 GB at Q4_K_M with an 8K context window. That is the 1.4 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 NinjaMouse 2.4B 32L Danube on an 8 GB GPU?
Yes, with Q6_K: the 2.0 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NinjaMouse 2.4B 32L Danube GGUF?
It depends on the quant: IQ1_S is 0.6 GB, IQ1_M is 0.6 GB, IQ2_XXS is 0.7 GB, IQ2_XS is 0.7 GB, IQ2_S is 0.8 GB, IQ2_M is 0.8 GB and 18 more.
What context length does NinjaMouse 2.4B 32L Danube support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.7 GB at 8K and 1.3 GB at 16K.
Where can I download NinjaMouse 2.4B 32L Danube GGUF?
The files are on Hugging Face in the mradermacher/NinjaMouse-2.4B-32L-danube-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 NinjaMouse 2.4B 32L Danube 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 NinjaMouse 2.4B 32L Danube on 8 GB VRAM?
Yes, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM, using approximately 1.7–1.8 GB of memory at 8k context.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.