llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 needs about 15.6 GB of memory at Q4_K_M (a 8.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 5.0 GB (Q2_K) to 13.9 GB (Q8_0).
13.1B parameter GPT‑2 style Japanese instruction model
The llm‑jp‑13b‑instruct‑full‑jaster‑dolly‑oasst‑v1.0 model is a 13.1 billion parameter GPT‑2 architecture trained on 2048‑token context. It is released under the Apache‑2.0 license and available in multiple GGUF quantizations.
Good at
- Japanese instruction following
- Large context handling
- Stable inference on low‑memory GPUs
Limits
- No vision support
- Requires 8 k context for memory estimates
- No explicit language list
Best for
- Japanese text generation
- Instruction‑driven chatbots
- Fine‑tuning Japanese datasets
Who it’s for. Developers building Japanese language applications who need a large‑scale instruction model. The model is suitable for users with access to GPU memory to run the desired quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.0 GB | 7.2 GB | Fits | Get file → | |
| Q3_K_S | 5.7 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_M | 6.9 GB | 9.1 GB | Too big | Get file → | |
| Q4_0 | 7.5 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_L | 7.5 GB | 9.7 GB | Too big | Get file → | |
| Q4_K_S | 7.6 GB | 9.8 GB | Too big | Get file → | |
| Q4_1 | 8.3 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q5_0 | 9.1 GB | 11.2 GB | Too big | Get file → | |
| Q5_K_S | 9.1 GB | 11.2 GB | Too big | Get file → | |
| Q5_K_M | 9.8 GB | 11.9 GB | Too big | Get file → | |
| Q5_1 | 9.9 GB | 12.0 GB | Too big | Get file → | |
| Q6_K | 10.8 GB | 12.9 GB | Too big | Get file → | |
| Q8_0 | 13.9 GB | 16.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 7.45 GB, memory 14.7 GB). For 12 GB VRAM, Q3_K_M (6.93 GB, 14.1 GB) or Q4_K_M (8.39 GB, 15.6 GB). For 16 GB VRAM, Q5_K_M (9.76 GB, 17 GB) or Q5_1 (9.86 GB, 17.1 GB).
What GPU do you need for llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q4_K_M (8.4 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.9 GB file, about 21.2 GB in use).
Which llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 quant should you choose?
Q4_K_M is the usual starting point for llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0: it balances file size and quality well. Here it is a 8.4 GB file.
The Q8_0 file is 13.9 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 5.0 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
Frequently asked questions about llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0
How much VRAM does llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 need?
About 15.6 GB at Q4_K_M with an 8K context window. That is the 8.4 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 llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 GGUF?
It depends on the quant: Q2_K is 5.0 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.9 GB, Q4_0 is 7.5 GB, Q3_K_L is 7.5 GB, Q4_K_S is 7.6 GB and 8 more.
What context length does llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.
Where can I download llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 GGUF?
The files are on Hugging Face in the mmnga/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-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-13b-instruct-full-jaster-dolly-oasst-v1.0 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?
Use the Q4_0 quantization; it requires about 14.7 GB of VRAM at 8 k context, so 8 GB is insufficient.
Is the model suitable for English text?
The model is primarily Japanese; English performance is not guaranteed.
Does the model support vision tasks?
No, the model has no vision capabilities.