Llm Jp 3 980m Instruct3 needs about 2.1 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.3 GB (IQ1_S) to 1.1 GB (Q8_0).
Japanese instruction-following LLM with 0.99B parameters
Llm Jp 3 980m Instruct3 is a 0.99B parameter transformer model trained on 2.1T tokens. It supports Japanese and English text generation and instruction following. The model is released under Apache‑2.0.
Good at
- Japanese instruction following
- Text generation
- Fine‑tuned alignment
Limits
- Context length 4096 tokens
- No vision support
- Requires at least 1.8 GB VRAM for IQ1_S
Best for
- Japanese chatbots
- Instruction‑based writing
- Low‑memory inference
Who it’s for. Developers building Japanese language assistants or educational tools who need a lightweight model with instruction‑following capabilities. The model is suitable for research and production environments that can run llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.3 GB | 1.3 GB | Fits | Get file → | |
| IQ1_M | 0.3 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XXS | 0.3 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 1.4 GB | Fits | Get file → | |
| IQ2_S | 0.4 GB | 1.4 GB | Fits | Get file → | |
| IQ2_M | 0.4 GB | 1.4 GB | Fits | Get file → | |
| Q2_K | 0.4 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XXS | 0.4 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XS | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_S | 0.5 GB | 1.5 GB | Fits | Get file → | |
| IQ3_S | 0.5 GB | 1.5 GB | Fits | Get file → | |
| IQ3_M | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ4_XS | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_0 | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ4_NL | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q5_0 | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 1.1 GB | 2.1 GB | Fits | Get file → |
For 8 GB VRAM, IQ1_S (0.3 GB file, 1.8 GB memory) or IQ1_M (0.32 GB file, 1.8 GB memory) are suitable. For 4 GB VRAM, IQ2_XXS (0.34 GB file, 1.8 GB memory) or IQ2_XS (0.36 GB file, 1.9 GB memory) are recommended. For 2 GB VRAM, IQ3_XXS (0.43 GB file, 1.9 GB memory) or IQ3_XS (0.47 GB file, 2 GB memory) can be used.
What GPU do you need for Llm Jp 3 980m Instruct3?
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 Q8_0 (1.1 GB file, about 2.6 GB in use).
Which Llm Jp 3 980m Instruct3 quant should you choose?
Q4_K_M is the usual starting point for Llm Jp 3 980m Instruct3: it balances file size and quality well. Here it is a 0.6 GB file.
The Q8_0 file is 1.1 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 IQ1_S at 0.3 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 Llm Jp 3 980m Instruct3
How much VRAM does Llm Jp 3 980m Instruct3 need?
About 2.1 GB at Q4_K_M with an 8K context window. That is the 0.6 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 Llm Jp 3 980m Instruct3 on an 8 GB GPU?
Yes, with Q8_0: the 1.1 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llm Jp 3 980m Instruct3 GGUF?
It depends on the quant: IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB, IQ2_M is 0.4 GB and 18 more.
What context length does Llm Jp 3 980m Instruct3 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.0 GB at 8K and 0.5 GB at 4K.
Where can I download Llm Jp 3 980m Instruct3 GGUF?
The files are on Hugging Face in the mmnga/llm-jp-3-980m-instruct3-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 Llm Jp 3 980m Instruct3 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 this model on 8 GB VRAM?
Yes, IQ1_S or IQ1_M quantizations use about 1.8 GB VRAM at 8 k context.
Does this model support vision?
No, the model has no vision capabilities.
Which quantization is best for 4 GB VRAM?
IQ2_XXS or IQ2_XS use roughly 1.8–1.9 GB VRAM, fitting within 4 GB.