Nobidog Qubo 1b 0.2 needs about 2.1 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.8 GB (Q4_K_M) to 2.4 GB (F16).
1.18B Japanese QUBO formulation model
Nobidog Qubo 1b 0.2 is a 1.18B‑parameter Llama‑style model trained to read Japanese optimization problems and output structured JSON for QUBO solvers. It supports 10 fixed problem types and a free‑form formulation mode.
Good at
- Japanese QUBO problem parsing
- Structured JSON output
- Fixed problem type handling
Limits
- No vision support
- Context limited to 2048 tokens
- Apache‑2.0 license
Best for
- Automated QUBO formulation
- Japanese optimization workflows
- Research prototyping
Who it’s for. Engineers and researchers working with Japanese optimization problems who need automated JSON formulation for QUBO solvers. The model is suitable for developers integrating QUBO pipelines in Japanese language contexts.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 1.3 GB | 2.0 GB | Fits | Get file → | |
| F16 | 2.4 GB | 3.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.77 GB, ~2.1 GB memory at 8k context). For 12 GB VRAM, Q8_0 (1.25 GB, ~2.6 GB memory) is a good balance. If 16 GB VRAM is available, F16 (2.36 GB, ~3.7 GB memory) offers the highest precision.
What GPU do you need for Nobidog Qubo 1b 0.2?
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 F16 (2.4 GB file, about 3.7 GB in use).
Which Nobidog Qubo 1b 0.2 quant should you choose?
Q4_K_M is the usual starting point for Nobidog Qubo 1b 0.2: it balances file size and quality well. Here it is a 0.8 GB file.
The Q8_0 file is 1.3 GB, about 1.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nobidog Qubo 1b 0.2
How much VRAM does Nobidog Qubo 1b 0.2 need?
About 2.1 GB at Q4_K_M with an 8K context window. That is the 0.8 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 Nobidog Qubo 1b 0.2 on an 8 GB GPU?
Yes, with F16: the 2.4 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nobidog Qubo 1b 0.2 GGUF?
It depends on the quant: Q4_K_M is 0.8 GB, Q8_0 is 1.3 GB, F16 is 2.4 GB.
What context length does Nobidog Qubo 1b 0.2 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.2 GB at 2K.
Where can I download Nobidog Qubo 1b 0.2 GGUF?
The files are on Hugging Face in the blueqat/nobidog-qubo-1b-0.2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Nobidog Qubo 1b 0.2 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 Nobidog Qubo 1b 0.2 on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 2.1 GB memory at 8k context, fitting within 8 GB VRAM.
Does the model support English?
The model is trained for Japanese input and output; English support is not specified.
Is there a free‑form QUBO formulation mode?
Yes, prefix the prompt with "言葉で定式化: " to obtain a free‑form JSON formulation.