Gumini 1B Base i1 needs about 1.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 26 quants, from 0.4 GB (IQ1_S) to 2.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.
Gumini 1B Base i1 – a 1.08B bilingual Korean‑English base model
Gumini 1B Base i1 is a 1.08B parameter base language model built by inheriting the first 10 layers of Qwen 2.5 3B and continuing pretraining on a Korean‑English corpus. It is not instruction‑tuned and produces text continuations. The model is released under a non‑commercial license.
Good at
- Bilingual Korean‑English text generation
- Base‑level language modeling
- Tool‑aware generation
Limits
- No instruction tuning or safety alignment
- High repetition risk without penalty
- Non‑commercial license only
Best for
- Research prototyping
- Low‑resource inference on edge devices
- Educational demonstrations
Who it’s for. Researchers and developers who need a lightweight Korean‑English base model for experimentation. The model is suitable for non‑commercial projects and educational use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ1_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_XXS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_S | 0.5 GB | 1.0 GB | Fits | Get file → | |
| IQ2_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ3_XXS | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q2_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q2_K | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ3_XS | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_S | 0.6 GB | 1.2 GB | Fits | Get file → | |
| IQ3_S | 0.6 GB | 1.2 GB | Fits | Get file → | |
| IQ3_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_L | 0.7 GB | 1.2 GB | Fits | Get file → | |
| IQ4_XS | 0.7 GB | 1.3 GB | Fits | Get file → | |
| IQ4_NL | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q4_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_S | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q4_1 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_S | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q6_K | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 1.7 GB | Fits | Get file → | |
| F16 | 2.2 GB | 2.8 GB | Fits | Get file → |
For 8 GB VRAM, use IQ4_XS (0.67 GB) or IQ3_M (0.60 GB) for a good balance of size and quality. If more VRAM is available, Q4_K_M (0.72 GB) or Q5_K_M (0.81 GB) provide higher fidelity. All estimates are approximate.
What GPU do you need for Gumini 1B Base i1?
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 (2.2 GB file, about 2.8 GB in use).
Which Gumini 1B Base i1 quant should you choose?
Q4_K_M is the usual starting point for Gumini 1B Base i1: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.2 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.
If memory is tight, the smallest file is IQ1_S at 0.4 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 Gumini 1B Base i1
How much VRAM does Gumini 1B Base i1 need?
About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 Gumini 1B Base i1 on an 8 GB GPU?
Yes, with F16: the 2.2 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gumini 1B Base i1 GGUF?
It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.5 GB, IQ2_M is 0.5 GB and 20 more.
What context length does Gumini 1B Base i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.3 GB at 32K.
Where can I download Gumini 1B Base i1 GGUF?
The files are on Hugging Face in the GuminiResearch/Gumini-1B-Base-i1-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 Gumini 1B Base i1 use?
Hugging Face lists the license as other. 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 Gumini 1B Base i1 on 8 GB VRAM?
Yes, quantizations such as IQ4_XS (0.67 GB) or IQ3_M (0.60 GB) fit within 8 GB VRAM with an estimated 1.3 GB memory usage at 8k context.
Is this model safe for production use?
No, it is a base model without instruction tuning or safety alignment and should not be used in safety‑critical contexts.
What license does the model use?
It is released under a Qwen Research License for non‑commercial or research use only.