VAGOsolutions SauerkrautLM 7b HerO needs about 3.0 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.4 GB (Q3_K_L) to 5.0 GB (Q5_0).
SauerkrautLM-7b-HerO – a bilingual 3.8B parameter model
SauerkrautLM-7b-HerO is a 3.8B parameter model created by merging Mistral‑based models and fine‑tuned on a German dataset. It supports English and German text generation. The model is distributed in GGUF format with multiple quantizations.
Good at
- German language understanding
- English‑German bilingual generation
- ChatML prompt handling
Limits
- No vision support
- License not specified
- No explicit context length info
Best for
- German‑English translation
- Bilingual chatbots
- German content creation
Who it’s for. Developers needing a bilingual LLM for German and English applications. The model is suitable for local deployment via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q8_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q3_K | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q5_1 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| IQ3_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q5_K | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q4_K | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| IQ4_NL | 2.3 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_S | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q2_K | 2.7 GB | 3.5 GB | Fits | Get file → | |
| Q3_K_S | 2.7 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XS | 3.0 GB | 3.9 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 3.9 GB | Fits | Get file → | |
| Q4_1 | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_S | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q5_0 | 5.0 GB | 6.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q3_K_L (0.4 GB, 0.9 GB memory) or Q3_K_M (0.54 GB, 1.1 GB memory). For 12 GB VRAM, Q4_K_M (2.23 GB, 3 GB memory) or Q5_K_M (0.95 GB, 1.6 GB memory) are good options. Larger VRAM allows higher‑quality quants such as Q5_0 (5 GB, 6.1 GB memory).
What GPU do you need for VAGOsolutions SauerkrautLM 7b HerO?
These figures add the file size, an fp16 KV cache at an 8K context window 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 IQ3_S (3.1 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (4.1 GB file, about 5.1 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_0 (5.0 GB file, about 6.1 GB in use).
Which VAGOsolutions SauerkrautLM 7b HerO quant should you choose?
Q4_K_M is the usual starting point for VAGOsolutions SauerkrautLM 7b HerO: it balances file size and quality well. Here it is a 2.2 GB file.
The Q8_0 file is 0.7 GB, about 0.3 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 Q3_K_L at 0.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about VAGOsolutions SauerkrautLM 7b HerO
How much VRAM does VAGOsolutions SauerkrautLM 7b HerO need?
About 3.0 GB at Q4_K_M with an 8K context window. That is the 2.2 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 VAGOsolutions SauerkrautLM 7b HerO on an 8 GB GPU?
Yes, with Q5_0: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VAGOsolutions SauerkrautLM 7b HerO GGUF?
It depends on the quant: Q3_K_L is 0.4 GB, Q3_K_M is 0.5 GB, Q8_0 is 0.7 GB, Q6_K is 0.8 GB, Q3_K is 0.8 GB, Q5_1 is 0.9 GB and 16 more.
Where can I download VAGOsolutions SauerkrautLM 7b HerO GGUF?
The files are on Hugging Face in the RichardErkhov/VAGOsolutions_-_SauerkrautLM-7b-HerO-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run SauerkrautLM-7b-HerO on 8 GB VRAM?
Yes, with a low‑precision quant like Q3_K_L or Q3_K_M, which use under 1 GB VRAM at 8 k context.
Does the model support German language tasks?
Yes, it is fine‑tuned on a German dataset and includes German in its language list.
What quant should I use for best performance on a 12 GB GPU?
Use Q4_K_M or Q5_K_M, which fit comfortably within 12 GB VRAM and provide higher quality than lower‑precision options.