Josev 9B needs about 7.3 GB of memory at Q4_K_M (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.7 GB (Q4_K_M) to 18.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Josev‑9B – a German decision model in GGUF format
Josev‑9B is a 9.08 billion‑parameter decision model trained on German decision tasks. It returns calibrated probabilities for each option without generating text. The model supports reasoning, tools, and vision abilities.
Good at
- Calibrated decision probabilities
- German language tasks
- Reasoning and tool use
Limits
- No text generation – output_tokens: 0
- Requires llama.cpp ≥ b11443
- License: apache‑2.0
Best for
- Decision‑making APIs
- German‑language classification
- Tool‑integrated workflows
Who it’s for. Developers building decision‑making services that need calibrated probabilities in German. The model is suitable for applications that require a classifier rather than a generative LLM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 7.5 GB | 9.0 GB | Too big | Get file → | |
| Q8_0 | 9.7 GB | 11.2 GB | Too big | Get file → | |
| BF16 | 18.2 GB | 19.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.72 GB, estimated 7.3 GB at 8 k context). For 12 GB VRAM, Q6_K (7.46 GB, 9 GB). For 16 GB VRAM, Q8_0 (9.66 GB, 11.2 GB). BF16 requires 18.16 GB and 19.7 GB memory.
What GPU do you need for Josev 9B?
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 Q4_K_M (5.7 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 11.2 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (18.2 GB file, about 19.7 GB in use).
Which Josev 9B quant should you choose?
Q4_K_M is the usual starting point for Josev 9B: it balances file size and quality well. Here it is a 5.7 GB file.
The Q8_0 file is 9.7 GB, about 1.7 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
Source
Frequently asked questions about Josev 9B
How much VRAM does Josev 9B need?
About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.7 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 Josev 9B on an 8 GB GPU?
Yes, with Q4_K_M: the 5.7 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 Josev 9B GGUF?
It depends on the quant: Q4_K_M is 5.7 GB, Q6_K is 7.5 GB, Q8_0 is 9.7 GB, BF16 is 18.2 GB.
What context length does Josev 9B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Josev 9B GGUF?
The files are on Hugging Face in the mayflowergmbh/Josev-9B-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 Josev 9B 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 Josev‑9B on 8 GB VRAM?
Yes, the Q4_K_M quantization uses 5.72 GB file size and estimates 7.3 GB VRAM at 8 k context, fitting within 8 GB.
Does Josev‑9B generate text?
No, it is a decision model that returns probability distributions; output_tokens is 0.
What license applies to Josev‑9B?
The model is released under the apache‑2.0 license.