Qwen3.5 2B_qlora_decisions De needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.3 GB (Q4_K_M) to 3.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Qwen3.5 2B_qlora_decisions De – a small German decision model
Qwen3.5 2B_qlora_decisions De is a 1.91B parameter Clef model fine‑tuned for decision tasks in German. It returns calibrated probabilities for typed questions (choice, noul, score) via the System One / Decision API. The model has no text generation capability.
Good at
- Decision probability estimation
- Calibrated multi‑type question handling
- Fast inference with small memory footprint
Limits
- No text generation
- Requires llama.cpp b11443 or newer
- Vision support not included
Best for
- Automated decision support in German
- Batch decision scoring
- Integration with System One API
Who it’s for. Developers building decision‑making services in German who need fast, calibrated probability outputs without generating text. The model is suitable for backend services that process structured decision queries.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 2.9 GB | Fits | Get file → | |
| BF16 | 3.8 GB | 4.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.29 GB, 2.2 GB memory at 8 k context). For 12 GB VRAM, Q6_K (1.58 GB, 2.5 GB memory) is a good balance. If more memory is available, Q8_0 (2.04 GB, 2.9 GB memory) or BF16 (3.84 GB, 4.7 GB memory) can be used for higher precision.
What GPU do you need for Qwen3.5 2B_qlora_decisions De?
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 Q8_0 (2.0 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.8 GB file, about 4.7 GB in use).
Which Qwen3.5 2B_qlora_decisions De quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 2B_qlora_decisions De: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.0 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Qwen3.5 2B_qlora_decisions De
How much VRAM does Qwen3.5 2B_qlora_decisions De need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Qwen3.5 2B_qlora_decisions De on an 8 GB GPU?
Yes, with BF16: the 3.8 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 2B_qlora_decisions De GGUF?
It depends on the quant: Q4_K_M is 1.3 GB, Q6_K is 1.6 GB, Q8_0 is 2.0 GB, BF16 is 3.8 GB.
What context length does Qwen3.5 2B_qlora_decisions De support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Qwen3.5 2B_qlora_decisions De GGUF?
The files are on Hugging Face in the johannhartmann/Qwen3.5-2B_qlora_decisions-de-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 Qwen3.5 2B_qlora_decisions De 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 1.29 GB and requires approximately 2.2 GB of VRAM at 8 k context.
Does this model support text generation?
No, it only returns decision probabilities and does not generate text.
What llama.cpp version is needed?
It requires llama.cpp version b11443 or newer, tested with b11541.