Viking 7B needs about 9.4 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.9 GB (IQ1_S) to 6.2 GB (Q6_K).
Viking 7B – 7.55B parameter decoder-only transformer
Viking 7B is a 7.55B parameter decoder-only transformer trained on Finnish, English, Swedish, Danish, Norwegian, Icelandic and code. It was trained on 2 trillion tokens on the LUMI supercomputer and is released under Apache 2.0.
Good at
- Coding tasks
- Multilingual text generation
- Basic translation between Scandinavian languages
Limits
- No vision support
- Requires 8k context for full performance
- Large VRAM needed for higher quants
Best for
- Local LLM deployment
- Code generation in Scandinavian languages
- Fine‑tuning for domain‑specific tasks
Who it’s for. Developers and researchers needing an open‑source, multilingual LLM that can be run locally. The model is suitable for those who can fine‑tune it for specific use cases.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.9 GB | 4.6 GB | Fits | Get file → | |
| IQ1_M | 2.1 GB | 4.7 GB | Fits | Get file → | |
| IQ2_XXS | 2.3 GB | 4.9 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 5.1 GB | Fits | Get file → | |
| IQ2_S | 2.7 GB | 5.3 GB | Fits | Get file → | |
| Q2_K_S | 2.8 GB | 5.4 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 5.5 GB | Fits | Get file → | |
| Q2_K | 3.0 GB | 5.7 GB | Fits | Get file → | |
| IQ3_XXS | 3.0 GB | 5.7 GB | Fits | Get file → | |
| IQ3_XS | 3.3 GB | 6.0 GB | Fits | Get file → | |
| IQ3_S | 3.5 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 6.1 GB | Fits | Get file → | |
| IQ3_M | 3.6 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_M | 3.8 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_L | 4.1 GB | 6.8 GB | Fits | Get file → | |
| IQ4_XS | 4.2 GB | 6.8 GB | Fits | Get file → | |
| IQ4_NL | 4.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_0 | 4.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_S | 4.4 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_M | 4.6 GB | 7.3 GB | Tight | Get file → | |
| Q4_1 | 4.8 GB | 7.5 GB | Tight | Get file → | |
| Q5_K_S | 5.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 5.4 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 6.2 GB | 8.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 4.65 GB, estimated memory 9.4 GB). For 12 GB VRAM, Q5_K_M (5.4 GB, 10.2 GB) or Q6_K (6.2 GB, 11 GB). Lower‑bit IQ quants such as IQ1_S (1.94 GB, 6.7 GB) are suitable for 4 GB VRAM setups.
What GPU do you need for Viking 7B?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is IQ3_XXS (3.0 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 11.0 GB in use).
Which Viking 7B quant should you choose?
Q4_K_M is the usual starting point for Viking 7B: it balances file size and quality well. Here it is a 4.6 GB file.
If memory is tight, the smallest file is IQ1_S at 1.9 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 Viking 7B
How much VRAM does Viking 7B need?
About 9.4 GB at Q4_K_M with an 8K context window. That is the 4.6 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 Viking 7B on an 8 GB GPU?
Yes, with IQ3_XXS: the 3.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Viking 7B GGUF?
It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.7 GB, Q2_K_S is 2.8 GB and 18 more.
What context length does Viking 7B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download Viking 7B GGUF?
The files are on Hugging Face in the mradermacher/Viking-7B-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 Viking 7B 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 Viking 7B on 8 GB VRAM?
Yes, using the Q4_K_M quant which requires approximately 9.4 GB of VRAM at 8k context.
Does Viking 7B support vision tasks?
No, Viking 7B is a text‑only model with no vision capabilities.
What license is Viking 7B released under?
Viking 7B is released under the Apache 2.0 license.