Ninja v1 128k 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). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Ninja v1 128k – 7.24B llama model with 128k token context
Ninja v1 128k is a 7.24B parameter llama model trained on 131072 token context. It is released under apache-2.0 and supports English and Japanese. The model is available in multiple GGUF quantizations.
Good at
- Large context reasoning
- Japanese language support
- Compact quant options
Limits
- No vision support
- Requires 8k context for memory estimates
- License is apache-2.0
Best for
- Chatbots needing long context
- Japanese text generation
- Fine‑tuning on custom data
Who it’s for. Developers building local LLM applications that require extended context windows and Japanese language capabilities. The model is suitable for users who can manage the memory demands of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.6 GB | 3.2 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 3.3 GB | Fits | Get file → | |
| IQ2_XXS | 2.0 GB | 3.6 GB | Fits | Get file → | |
| IQ2_XS | 2.2 GB | 3.8 GB | Fits | Get file → | |
| IQ2_S | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ2_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q2_K | 2.7 GB | 4.3 GB | Fits | Get file → | |
| IQ3_XXS | 2.8 GB | 4.4 GB | Fits | Get file → | |
| IQ3_XS | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_S | 3.2 GB | 4.7 GB | Fits | Get file → | |
| IQ3_S | 3.2 GB | 4.8 GB | Fits | Get file → | |
| IQ3_M | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_M | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_L | 3.8 GB | 5.4 GB | Fits | Get file → | |
| IQ4_XS | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.7 GB | Fits | Get file → | |
| IQ4_NL | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_S | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.9 GB | Fits | Get file → | |
| Q5_0 | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_S | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 5.1 GB | 6.7 GB | Fits | Get file → | |
| Q6_K | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q8_0 | 7.7 GB | 9.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS (2.2 GB file, 3.8 GB memory) or Q2_K (2.72 GB file, 4.3 GB memory). For 12 GB VRAM, Q3_K_M (3.52 GB file, 5.1 GB memory) or Q4_K_M (4.37 GB file, 5.9 GB memory) are good choices. Higher quant levels increase quality but also memory usage.
What GPU do you need for Ninja v1 128k?
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 128k quant should you choose?
Q4_K_M is the usual starting point for Ninja v1 128k: 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 128k
How much VRAM does Ninja v1 128k 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 128k 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 128k 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 128k support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Ninja v1 128k GGUF?
The files are on Hugging Face in the mmnga/Ninja-v1-128k-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 128k 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 128k on 8 GB VRAM?
Yes, with a low‑memory quant such as IQ2_XS or Q2_K, which use about 4 GB of VRAM at 8k context.
Does the model support Japanese?
Yes, the model was trained with Japanese data and includes Japanese language support.
What license does the model use?
The model is released under the apache-2.0 license.