Lumina 2 i1 needs about 12.8 GB of memory at Q4_K_M (a 11.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 22 quants, from 3.9 GB (IQ1_S) to 15.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Lumina 2 i1 – 18.5B Sparse Mixture of Experts LLaMA model
Lumina 2 i1 is an 18.5B‑parameter sparse Mixture of Experts LLaMA model. It supports a 32,768‑token context window and is released under the Apache‑2.0 license. The model is available in a variety of GGUF quantizations.
Good at
- Large context generation
- Sparse expert inference
- LLM fine‑tuning
Limits
- No vision support
- Requires 8,000‑token context for memory estimates
- Apache‑2.0 license
Best for
- Chatbots needing long context
- Research on sparse LLMs
- Custom fine‑tuning pipelines
Who it’s for. Developers and researchers who need a large‑scale LLaMA model with sparse expert capabilities and a generous context window. The model is suitable for applications that can handle the memory demands of the larger quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ1_M | 4.3 GB | 5.8 GB | Fits | Get file → | |
| IQ2_XXS | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ2_XS | 5.5 GB | 7.1 GB | Fits | Get file → | |
| IQ2_S | 5.6 GB | 7.2 GB | Tight | Get file → | |
| IQ2_M | 6.2 GB | 7.7 GB | Tight | Get file → | |
| Q2_K_S | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q2_K | 6.8 GB | 8.4 GB | Too big | Get file → | |
| IQ3_XXS | 7.1 GB | 8.7 GB | Too big | Get file → | |
| IQ3_XS | 7.6 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_S | 8.0 GB | 9.6 GB | Too big | Get file → | |
| IQ3_S | 8.0 GB | 9.6 GB | Too big | Get file → | |
| IQ3_M | 8.2 GB | 9.8 GB | Too big | Get file → | |
| Q3_K_M | 8.9 GB | 10.5 GB | Too big | Get file → | |
| Q3_K_L | 9.6 GB | 11.2 GB | Too big | Get file → | |
| IQ4_XS | 9.9 GB | 11.5 GB | Too big | Get file → | |
| Q4_0 | 10.5 GB | 12.1 GB | Too big | Get file → | |
| Q4_K_S | 10.5 GB | 12.1 GB | Too big | Get file → | |
| Q4_K_M | 11.2 GB | 12.8 GB | Too big | Get file → | |
| Q5_K_S | 12.8 GB | 14.3 GB | Too big | Get file → | |
| Q5_K_M | 13.1 GB | 14.7 GB | Too big | Get file → | |
| Q6_K | 15.2 GB | 16.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (3.88 GB) or IQ1_M (4.27 GB). For 12 GB VRAM, IQ2_XS (5.48 GB) or IQ2_S (5.64 GB) are good choices. For 16 GB VRAM, Q4_K_M (11.2 GB) or Q5_K_M (13.13 GB) provide higher quality while staying within budget. Memory estimates are approximate.
What GPU do you need for Lumina 2 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is IQ1_M (4.3 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_S (6.3 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (9.9 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (13.1 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (15.2 GB file, about 16.8 GB in use).
Which Lumina 2 i1 quant should you choose?
Q4_K_M is the usual starting point for Lumina 2 i1: it balances file size and quality well. Here it is a 11.2 GB file.
If memory is tight, the smallest file is IQ1_S at 3.9 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 Lumina 2 i1
How much VRAM does Lumina 2 i1 need?
About 12.8 GB at Q4_K_M with an 8K context window. That is the 11.2 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 Lumina 2 i1 on an 8 GB GPU?
Yes, with Q2_K_S: the 6.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Lumina 2 i1 GGUF?
It depends on the quant: IQ1_S is 3.9 GB, IQ1_M is 4.3 GB, IQ2_XXS is 4.9 GB, IQ2_XS is 5.5 GB, IQ2_S is 5.6 GB, IQ2_M is 6.2 GB and 16 more.
What context length does Lumina 2 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 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Lumina 2 i1 GGUF?
The files are on Hugging Face in the mradermacher/Lumina-2-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 Lumina 2 i1 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 Lumina 2 i1 on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations, which are 3.88 GB and 4.27 GB respectively. The estimated VRAM usage at 8,000‑token context is 5.5 GB and 5.8 GB.
Does Lumina 2 i1 support vision tasks?
No, the model has no vision capabilities.
What license applies to Lumina 2 i1?
The model is released under the Apache‑2.0 license.