Teuken 7B Instruct v0.6 needs about 5.8 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 6.5 GB (Q6_K).
Teuken 7B Instruct v0.6 – 7.45B multilingual instruction‑tuned LLM
Teuken 7B Instruct v0.6 is a 7.45B parameter transformer decoder model tuned for instruction following. It supports 24 official EU languages and is released under cc‑by‑nc‑4.0. The model is designed for research, educational and private use.
Good at
- Multilingual instruction following
- Stable performance across EU languages
- Research‑grade LLM
Limits
- Not suited for math or coding tasks
- Requires prompt template
- No vision support
Best for
- Multilingual chatbots
- Academic language studies
- European policy analysis
Who it’s for. Researchers and developers needing a multilingual LLM for European languages. The model is free for non‑commercial use and can be run locally with GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ1_S | 2.7 GB | 3.3 GB | Fits | Get file → | |
| IQ1_M | 2.8 GB | 3.4 GB | Fits | Get file → | |
| IQ2_XXS | 2.9 GB | 3.6 GB | Fits | Get file → | |
| IQ2_XS | 3.1 GB | 3.7 GB | Fits | Get file → | |
| IQ2_S | 3.1 GB | 3.8 GB | Fits | Get file → | |
| IQ2_M | 3.3 GB | 3.9 GB | Fits | Get file → | |
| Q2_K_S | 3.4 GB | 4.0 GB | Fits | Get file → | |
| Q2_K | 3.4 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XXS | 3.5 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XS | 3.7 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 4.5 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 4.5 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 5.0 GB | Fits | Get file → | |
| IQ4_XS | 4.3 GB | 5.0 GB | Fits | Get file → | |
| IQ4_NL | 4.5 GB | 5.1 GB | Fits | Get file → | |
| Q4_0 | 4.5 GB | 5.1 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 5.3 GB | Fits | Get file → | |
| Q4_1 | 4.9 GB | 5.5 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 5.7 GB | Fits | Get file → | |
| Q5_K_S | 5.4 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_M | 5.7 GB | 6.3 GB | Fits | Get file → | |
| Q6_K | 6.5 GB | 7.2 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S (2.66 GB, 3.4 GB memory) or Q2_K (3.43 GB, 4.2 GB memory). With 12 GB VRAM, Q3_K_M (4.15 GB, 4.9 GB memory) or Q4_K_M (5.02 GB, 5.8 GB memory) are suitable. Larger VRAM allows Q5_K_M (5.65 GB, 6.4 GB memory) or Q6_K (6.55 GB, 7.3 GB memory).
What GPU do you need for Teuken 7B Instruct v0.6?
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 IQ2_M (3.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (5.0 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.5 GB file, about 7.3 GB in use).
Which Teuken 7B Instruct v0.6 quant should you choose?
Q4_K_M is the usual starting point for Teuken 7B Instruct v0.6: it balances file size and quality well. Here it is a 5.0 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 Teuken 7B Instruct v0.6
How much VRAM does Teuken 7B Instruct v0.6 need?
About 5.8 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Teuken 7B Instruct v0.6 on an 8 GB GPU?
Yes, with Q6_K: the 6.5 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Teuken 7B Instruct v0.6 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.7 GB, IQ1_M is 2.8 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.1 GB and 19 more.
What context length does Teuken 7B Instruct v0.6 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.1 GB at 4K.
Where can I download Teuken 7B Instruct v0.6 GGUF?
The files are on Hugging Face in the mradermacher/Teuken-7B-instruct-v0.6-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 Teuken 7B Instruct v0.6 use?
Hugging Face lists the license as cc-by-nc-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 Teuken 7B Instruct v0.6 on 8 GB VRAM?
Yes, use IQ1_S or Q2_K quantizations, which fit within 8 GB VRAM and use about 3.4–4.2 GB of memory.
Does the model support vision tasks?
No, the model is a text‑only transformer and has no vision capability.
Is the model free for commercial use?
No, the model is licensed under cc‑by‑nc‑4.0 and is for non‑commercial use only.