Josev 4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.7 GB (Q4_K_M) to 8.5 GB (BF16).
Josev 4B – a German‑trained decision model in GGUF format
Josev 4B is a 4.24 billion‑parameter decision model trained on German data. It answers typed questions and returns calibrated probabilities. The model is available in several GGUF quantizations for llama.cpp.
Good at
- German decision tasks
- Calibrated probability outputs
- Typed question answering
Limits
- Requires 16 k context
- No vision support
- Apache‑2.0 license
Best for
- Automated contract review
- German legal decision support
- Chatbot decision logic
Who it’s for. Developers building German‑language decision systems or chatbots that need calibrated probability outputs. The model is suitable for applications that require typed question answering and decision logic in German.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 8.5 GB | 10.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (2.74 GB file, ~4.3 GB memory). For 12 GB VRAM, Q6_K (3.49 GB file, ~5.1 GB memory). For 16 GB VRAM, Q8_0 (4.52 GB file, ~6.1 GB memory). BF16 needs ~10.1 GB memory.
What GPU do you need for Josev 4B?
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 Q6_K (3.5 GB file, about 5.1 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.5 GB file, about 10.1 GB in use).
Which Josev 4B quant should you choose?
Q4_K_M is the usual starting point for Josev 4B: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 4.5 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 4B
How much VRAM does Josev 4B need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.5 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 Josev 4B GGUF?
It depends on the quant: Q4_K_M is 2.7 GB, Q6_K is 3.5 GB, Q8_0 is 4.5 GB, BF16 is 8.5 GB.
What context length does Josev 4B support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.1 GB at 8K and 2.1 GB at 16K.
Where can I download Josev 4B GGUF?
The files are on Hugging Face in the mayflowergmbh/Josev-4B-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 4B 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 4B on 8 GB VRAM?
Yes, the Q4_K_M quantization uses about 4.3 GB of VRAM at 8 k context, which fits within 8 GB. The file size is 2.74 GB.
Does Josev 4B support vision?
No, the model does not include vision capabilities. It is a text‑only decision model.
What license is Josev 4B released under?
Josev 4B is released under the Apache‑2.0 license, allowing free use and modification.