Ozan v1 12B needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 7.5 GB (Q4_K_M) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
12B creative‑writing model with low slop, tuned from Mistral‑Nemo‑Instruct
Ozan v1 12B is a 12.2 B parameter model fine‑tuned for long‑form fiction. It reduces slop and repetition compared to its base. The model is trained on low‑slop examples and preference‑tuned to public‑domain prose.
Good at
- Low slop in creative writing
- Long‑form fiction generation
- Strong voice and tone
Limits
- No vision or multimodal support
- Requires 8k context for full performance
- Apache‑2.0 license
Best for
- Creative writing tasks
- Fiction drafting
- Storytelling assistance
Who it’s for. Writers, content creators, and developers who need a low‑slop, high‑quality fiction model. The model is suitable for projects that require natural prose without typical LLM artifacts.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 7.48 GB, ~9.3 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (8.73 GB, ~10.6 GB). For 16 GB VRAM use Q6_K (10.06 GB, ~11.9 GB). For 20 GB VRAM use Q8_0 (13.02 GB, ~14.9 GB).
What GPU do you need for Ozan v1 12B?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
Which Ozan v1 12B quant should you choose?
Q4_K_M is the usual starting point for Ozan v1 12B: it balances file size and quality well. Here it is a 7.5 GB file.
The Q8_0 file is 13.0 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 Ozan v1 12B
How much VRAM does Ozan v1 12B need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Ozan v1 12B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ozan v1 12B GGUF?
It depends on the quant: Q4_K_M is 7.5 GB, Q5_K_M is 8.7 GB, Q6_K is 10.1 GB, Q8_0 is 13.0 GB.
What context length does Ozan v1 12B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Ozan v1 12B GGUF?
The files are on Hugging Face in the arbazsiddiqui/Ozan-v1-12B-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 Ozan v1 12B 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 Ozan v1 12B on 8 GB VRAM?
Yes, with the Q4_K_M quant which requires about 9.3 GB memory at 8k context.
Does this model support vision or multimodal inputs?
No, it only handles text.