IRIS 18B SFT needs about 11.9 GB of memory at Q4_K_M (a 10.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 14.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
IRIS 18B SFT – 18B parameter LLM with Mixture of Experts
IRIS 18B SFT is a 18 billion parameter model built on the ernie4_5‑moe architecture. It supports a context length of 131 072 tokens and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Large context handling
- Mixture of Experts architecture
- Apache‑2.0 licensed
Limits
- No vision support
- Requires large VRAM for higher quants
- No active parameter count provided
Best for
- Long‑form content generation
- Research prototyping
- Chat applications with extended context
Who it’s for. Developers and researchers needing a large‑scale LLM with extended context. The model is suitable for those who can manage the memory requirements of higher‑quality quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 3.7 GB | 4.7 GB | Fits | Get file → | |
| IQ1_M | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ2_XXS | 4.8 GB | 5.8 GB | Fits | Get file → | |
| IQ2_XS | 5.3 GB | 6.3 GB | Fits | Get file → | |
| IQ2_S | 5.4 GB | 6.4 GB | Fits | Get file → | |
| IQ2_M | 5.9 GB | 6.9 GB | Fits | Get file → | |
| Q2_K_S | 6.2 GB | 7.1 GB | Fits | Get file → | |
| Q2_K | 6.7 GB | 7.6 GB | Tight | Get file → | |
| IQ3_XXS | 7.0 GB | 8.0 GB | Tight | Get file → | |
| IQ3_XS | 7.4 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_S | 7.9 GB | 8.8 GB | Too big | Get file → | |
| IQ3_S | 7.9 GB | 8.8 GB | Too big | Get file → | |
| IQ3_M | 7.9 GB | 8.9 GB | Too big | Get file → | |
| Q3_K_M | 8.7 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_L | 9.4 GB | 10.4 GB | Too big | Get file → | |
| IQ4_XS | 9.7 GB | 10.6 GB | Too big | Get file → | |
| IQ4_NL | 10.2 GB | 11.2 GB | Too big | Get file → | |
| Q4_0 | 10.2 GB | 11.2 GB | Too big | Get file → | |
| Q4_K_S | 10.3 GB | 11.2 GB | Too big | Get file → | |
| Q4_K_M | 10.9 GB | 11.9 GB | Too big | Get file → | |
| Q4_1 | 11.3 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_S | 12.4 GB | 13.4 GB | Too big | Get file → | |
| Q5_K_M | 12.8 GB | 13.8 GB | Too big | Get file → | |
| Q6_K | 14.8 GB | 15.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.7 GB) or IQ1_M (5.1 GB). If 12 GB VRAM is available, Q3_K_M (9.6 GB) or Q4_K_M (11.9 GB) are good choices. Larger quants such as Q5_K_M or Q6_K require more than 13 GB VRAM.
What GPU do you need for IRIS 18B SFT?
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 the main file (0.0 GB file, about 1.0 GB in use).
- 6 GB VRAM: the best quant that fits is IQ2_XXS (4.8 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XXS (7.0 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (10.9 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (14.8 GB file, about 15.8 GB in use).
Which IRIS 18B SFT quant should you choose?
Q4_K_M is the usual starting point for IRIS 18B SFT: it balances file size and quality well. Here it is a 10.9 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 IRIS 18B SFT
How much VRAM does IRIS 18B SFT need?
About 11.9 GB at Q4_K_M with an 8K context window. That is the 10.9 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 IRIS 18B SFT on an 8 GB GPU?
Yes, with IQ3_XXS: the 7.0 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of IRIS 18B SFT GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.7 GB, IQ1_M is 4.1 GB, IQ2_XXS is 4.8 GB, IQ2_XS is 5.3 GB, IQ2_S is 5.4 GB and 19 more.
What context length does IRIS 18B SFT support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download IRIS 18B SFT GGUF?
The files are on Hugging Face in the mradermacher/IRIS-18B-SFT-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 IRIS 18B SFT 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 IRIS 18B SFT on 8 GB VRAM?
Yes, with the IQ1_S or IQ1_M quantization, which use approximately 4.7 GB and 5.1 GB of VRAM at 8 k context.
Does the model support vision tasks?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.