Helium 1 2b Science needs about 2.7 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.7 GB (Q6_K).
Helium 1 2b Science – a 2.02B‑parameter LLM for European languages
Helium 1 2b Science is a 2.02B‑parameter language model based on the Helium family. It supports 24 official EU languages and is distributed under CC‑BY‑SA‑4.0. The model is not fine‑tuned for instruction following and should be aligned for downstream use.
Good at
- Research and development of NLP systems
- Language generation and understanding in EU languages
- Edge and mobile deployment
Limits
- Not fine‑tuned for instruction following
- No vision support
- Requires alignment for downstream use
Best for
- Prototype language models on limited hardware
- Academic research on EU language coverage
- Low‑resource deployment scenarios
Who it’s for. Researchers and developers needing a lightweight, multilingual LLM for the 24 EU languages. The model is suitable for experimentation and prototyping but should be fine‑tuned before production use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 0.5 GB | 1.5 GB | Fits | Get file → | |
| IQ1_M | 0.5 GB | 1.5 GB | Fits | Get file → | |
| IQ2_XXS | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ2_XS | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ2_S | 0.7 GB | 1.7 GB | Fits | Get file → | |
| IQ2_M | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q2_K_S | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q2_K | 0.8 GB | 1.8 GB | Fits | Get file → | |
| IQ3_XXS | 0.8 GB | 1.8 GB | Fits | Get file → | |
| IQ3_XS | 0.9 GB | 1.9 GB | Fits | Get file → | |
| IQ3_S | 0.9 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 1.9 GB | Fits | Get file → | |
| IQ3_M | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_M | 1.0 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_L | 1.1 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.1 GB | 2.1 GB | Fits | Get file → | |
| IQ4_NL | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_0 | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_M | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q4_1 | 1.3 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.4 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.4 GB | Fits | Get file → | |
| Q6_K | 1.7 GB | 2.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.24 GB, 2.7 GB memory at 8k context) or Q5_K_M (1.45 GB, 2.9 GB memory). For 4 GB VRAM, use IQ1_S (0.5 GB, 1.9 GB memory) or IQ1_M (0.54 GB, 2 GB memory). Smaller quants such as IQ2_XXS (0.6 GB, 2 GB memory) are also viable for tighter budgets. Estimates are approximate.
What GPU do you need for Helium 1 2b Science?
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 Q6_K (1.7 GB file, about 3.1 GB in use).
Which Helium 1 2b Science quant should you choose?
Q4_K_M is the usual starting point for Helium 1 2b Science: it balances file size and quality well. Here it is a 1.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Helium 1 2b Science
How much VRAM does Helium 1 2b Science need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.2 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 Helium 1 2b Science on an 8 GB GPU?
Yes, with Q6_K: the 1.7 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Helium 1 2b Science GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.5 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.6 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.7 GB and 19 more.
What context length does Helium 1 2b Science support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.5 GB at 4K.
Where can I download Helium 1 2b Science GGUF?
The files are on Hugging Face in the mradermacher/helium-1-2b-science-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 Helium 1 2b Science use?
Hugging Face lists the license as cc-by-sa-4.0. 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 Helium 1 2b Science on 8 GB VRAM?
Yes, the Q4_K_M quant uses 1.24 GB and requires about 2.7 GB of VRAM at 8k context.
Does this model support vision tasks?
No, Helium 1 2b Science is a text‑only language model.
What license applies to this model?
The model is released under CC‑BY‑SA‑4.0 and follows the Gemma Terms of Use.