Teuken 7B instruct research v0.4 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 17 quants, from 3.4 GB (Q2_K) to 7.9 GB (Q8_0).
7B multilingual instruction‑tuned LLM
Teuken 7B instruct research v0.4 is a 7.45B parameter transformer model tuned for instruction following. It supports 24 EU languages and is trained on 4T tokens. The model is available in multiple GGUF quantizations for llama.cpp.
Good at
- Multilingual instruction following
- Stable EU language coverage
- Research‑grade performance
Limits
- No vision support
- License is other, not open source
- Requires 8k context for estimates
Best for
- Multilingual chatbots
- Research in EU languages
- Instruction‑driven text generation
Who it’s for. Developers and researchers needing a multilingual LLM that covers all 24 EU languages. It is suitable for applications that require instruction following in European languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.4 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 4.5 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 → | |
| Q4_0 | 4.5 GB | 5.1 GB | Fits | Get file → | |
| Q4_0 | 4.5 GB | 5.1 GB | Fits | Get file → | |
| Q4_0 | 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_0 | 5.3 GB | 5.9 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 → | |
| Q5_1 | 5.7 GB | 6.3 GB | Fits | Get file → | |
| Q6_K | 6.5 GB | 7.2 GB | Fits | Get file → | |
| Q8_0 | 7.9 GB | 8.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (4.46 GB file, 5.2 GB memory). For 6 GB VRAM, use Q3_K_M (4.15 GB file, 4.9 GB memory). For 4 GB VRAM, use Q2_K (3.43 GB file, 4.2 GB memory). Memory estimates are approximate.
What GPU do you need for Teuken 7B instruct research v0.4?
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 Q5_0 (5.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.5 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 8.7 GB in use).
Which Teuken 7B instruct research v0.4 quant should you choose?
Q4_K_M is the usual starting point for Teuken 7B instruct research v0.4: it balances file size and quality well. Here it is a 5.0 GB file.
The Q8_0 file is 7.9 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 3.4 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 Teuken 7B instruct research v0.4
How much VRAM does Teuken 7B instruct research v0.4 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 research v0.4 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 research v0.4 GGUF?
It depends on the quant: Q2_K is 3.4 GB, Q3_K_S is 3.8 GB, Q3_K_M is 4.1 GB, Q3_K_L is 4.3 GB, Q4_0 is 4.5 GB, Q4_0 is 4.5 GB and 11 more.
What context length does Teuken 7B instruct research v0.4 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 research v0.4 GGUF?
The files are on Hugging Face in the QuantFactory/Teuken-7B-instruct-research-v0.4-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 research v0.4 use?
Hugging Face lists the license as other. 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 Q4_0 on 8 GB VRAM?
Yes, Q4_0 requires about 5.2 GB of VRAM at 8k context, which fits within 8 GB.
Is there a version for 4 GB VRAM?
Use Q2_K; it needs about 4.2 GB of VRAM at 8k context.
Does the model support vision tasks?
No, the model is text‑only and does not support vision.