Ninja v1 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.6 GB (IQ1_S) to 7.7 GB (Q8_0).
Ninja v1 – 7.24B llama model in GGUF format
Ninja v1 is a 7.24‑billion‑parameter llama architecture model converted to GGUF by mmnga. It supports a 4096‑token context window and is released under the apache‑2.0 license. The model is available in multiple quantizations ranging from IQ1_S to Q8_0.
Good at
- Japanese language support
- Large context handling
- Flexible quantization
Limits
- No vision capability
- Requires 8‑k context for memory estimates
- No explicit language list
Best for
- Local Japanese text generation
- Fine‑tuning on small datasets
- Running on mid‑range GPUs
Who it’s for. Developers and researchers who need a Japanese‑focused llama model for local deployment. The model is suitable for those who prefer open‑source licensing and flexible quantization options.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.6 GB | 2.6 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 2.8 GB | Fits | Get file → | |
| IQ2_XXS | 2.0 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XS | 2.2 GB | 3.2 GB | Fits | Get file → | |
| IQ2_S | 2.3 GB | 3.3 GB | Fits | Get file → | |
| IQ2_M | 2.5 GB | 3.5 GB | Fits | Get file → | |
| Q2_K | 2.7 GB | 3.8 GB | Fits | Get file → | |
| IQ3_XXS | 2.8 GB | 3.9 GB | Fits | Get file → | |
| IQ3_XS | 3.0 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_S | 3.2 GB | 4.2 GB | Fits | Get file → | |
| IQ3_S | 3.2 GB | 4.2 GB | Fits | Get file → | |
| IQ3_M | 3.3 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_M | 3.5 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_L | 3.8 GB | 4.9 GB | Fits | Get file → | |
| IQ4_XS | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ4_NL | 4.1 GB | 5.2 GB | Fits | Get file → | |
| Q4_K_S | 4.1 GB | 5.2 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q5_0 | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_S | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_M | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q6_K | 5.9 GB | 7.0 GB | Fits | Get file → | |
| Q8_0 | 7.7 GB | 8.7 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ2_XS (2.2 GB, 3.8 GB memory) or Q3_K_S (3.16 GB, 4.7 GB memory). With 12‑GB VRAM, Q4_K_M (4.37 GB, 5.9 GB memory) or Q5_K_M (5.13 GB, 6.7 GB memory) are recommended. Larger VRAM allows Q6_K or Q8_0 for higher quality.
What GPU do you need for Ninja v1?
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 IQ2_S (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
Which Ninja v1 quant should you choose?
Q4_K_M is the usual starting point for Ninja v1: it balances file size and quality well. Here it is a 4.4 GB file.
The Q8_0 file is 7.7 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 IQ1_S at 1.6 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 Ninja v1
How much VRAM does Ninja v1 need?
About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Ninja v1 on an 8 GB GPU?
Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ninja v1 GGUF?
It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 18 more.
What context length does Ninja v1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.
Where can I download Ninja v1 GGUF?
The files are on Hugging Face in the mmnga/Ninja-v1-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 Ninja v1 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 Ninja v1 on 8 GB VRAM?
Yes, using IQ2_XS or Q3_K_S quantizations will fit within 8‑GB VRAM with estimated memory usage of 3.8 or 4.7 GB at 8‑k context.
Does Ninja v1 support vision tasks?
No, the model has no vision capability.