Gumini 1.5B Base i1 needs about 1.6 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 26 quants, from 0.5 GB (IQ1_S) to 3.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.5 GB.
Gumini 1.5B Base i1 – a bilingual Korean‑English base language model
Gumini 1.5B Base i1 is a 1.54 billion‑parameter model built on Qwen2 architecture. It is a base model, not instruction‑tuned, and produces text continuations. The model was trained with the Inheritune progressive layer growing method on a Korean‑English corpus.
Good at
- Text generation in Korean and English
- Low‑resource inference with small quantizations
- Fast generation on llama.cpp
Limits
- No instruction tuning or safety alignment
- High repetition risk without penalty
- Non‑commercial license only
Best for
- Research prototypes
- Edge inference on low‑VRAM devices
- Educational demos
Who it’s for. Researchers and developers needing a bilingual Korean‑English base model for text generation tasks. The model is suitable for non‑commercial use and requires a Qwen Research license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ1_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ2_XXS | 0.5 GB | 1.2 GB | Fits | Get file → | |
| IQ2_XS | 0.6 GB | 1.2 GB | Fits | Get file → | |
| IQ2_S | 0.6 GB | 1.2 GB | Fits | Get file → | |
| IQ2_M | 0.6 GB | 1.3 GB | Fits | Get file → | |
| Q2_K_S | 0.7 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XXS | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q2_K | 0.7 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XS | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 1.4 GB | Fits | Get file → | |
| IQ3_S | 0.8 GB | 1.4 GB | Fits | Get file → | |
| IQ3_M | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.9 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ4_NL | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_0 | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_S | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_1 | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 1.1 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.3 GB | Fits | Get file → | |
| F16 | 3.1 GB | 3.7 GB | Fits | Get file → |
For 8 GB VRAM, use IQ4_XS (0.92 GB) or IQ3_M (0.81 GB). For 4 GB VRAM, IQ1_S (0.47 GB) or IQ1_M (0.5 GB) are recommended. For best quality on 16 GB VRAM, Q8_0 (1.65 GB) or Q6_K (1.27 GB) provide higher fidelity.
What GPU do you need for Gumini 1.5B 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 (3.1 GB file, about 3.7 GB in use).
Which Gumini 1.5B Base i1 quant should you choose?
Q4_K_M is the usual starting point for Gumini 1.5B Base i1: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.6 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 0.5 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 1.5B Base i1
How much VRAM does Gumini 1.5B Base i1 need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 1.0 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 1.5B Base i1 on an 8 GB GPU?
Yes, with F16: the 3.1 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 Gumini 1.5B Base i1 GGUF?
It depends on the quant: IQ1_S is 0.5 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB, IQ2_M is 0.6 GB and 20 more.
What context length does Gumini 1.5B 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 0.5 GB at 32K.
Where can I download Gumini 1.5B Base i1 GGUF?
The files are on Hugging Face in the GuminiResearch/Gumini-1.5B-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 1.5B 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 1.5B Base i1 on 8 GB VRAM?
Yes, quantizations such as IQ4_XS or IQ3_M fit within 8 GB VRAM and use approximately 1.6 GB of memory at 8k context.
Does this model support vision tasks?
No, the model is a text‑only base model with no vision capabilities.
Is the model safe for commercial deployment?
The model is licensed for non‑commercial or research use only; commercial use requires contacting Alibaba Cloud.