HOTHUN Stheno 3.2 v1.4 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.7 GB (Q4_0) to 16.1 GB.
HOTHUN Stheno 3.2 v1.4 – 8.03B Hungarian‑only LLaMA model
HOTHUN Stheno 3.2 v1.4 is an 8.03B parameter LLaMA model fine‑tuned exclusively in Hungarian. It supports a 8192 token context window and is released under cc‑by‑nc‑4.0. The model is tailored for private chat with NSFW capabilities.
Good at
- Hungarian language support
- Private chat NSFW handling
- Maintains original model style
Limits
- No vision support
- License restricts commercial use
- Requires 8.2+ GB VRAM for Q4_0
Best for
- Private Hungarian chatbots
- NSFW content moderation
- Local LLM deployment on mobile
Who it’s for. Developers building private Hungarian chat applications or local LLM services that need NSFW handling. The model is suitable for users who prefer non‑commercial, open‑source solutions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 4.7 GB | 6.2 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| BF16 | 16.1 GB | 17.6 GB | Too big | Get file → | |
| — | 16.1 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_0 quantized file (4.66 GB, ~6.2 GB memory at 8k context). If more VRAM is available, Q4_K_M (4.92 GB, ~6.5 GB memory) offers slightly better quality. BF16 requires 16.07 GB and ~17.6 GB memory, which exceeds typical mobile VRAM.
What GPU do you need for HOTHUN Stheno 3.2 v1.4?
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 (4.9 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 17.6 GB in use).
Which HOTHUN Stheno 3.2 v1.4 quant should you choose?
Q4_K_M is the usual starting point for HOTHUN Stheno 3.2 v1.4: it balances file size and quality well. Here it is a 4.9 GB file.
If memory is tight, the smallest file is Q4_0 at 4.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about HOTHUN Stheno 3.2 v1.4
How much VRAM does HOTHUN Stheno 3.2 v1.4 need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 HOTHUN Stheno 3.2 v1.4 on an 8 GB GPU?
Yes, with Q4_K_M: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of HOTHUN Stheno 3.2 v1.4 GGUF?
It depends on the quant: Q4_0 is 4.7 GB, Q4_0 is 4.7 GB, Q4_K_M is 4.9 GB, Q4_K_M is 4.9 GB, BF16 is 16.1 GB, file is 16.1 GB.
What context length does HOTHUN Stheno 3.2 v1.4 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download HOTHUN Stheno 3.2 v1.4 GGUF?
The files are on Hugging Face in the Mykee/HOTHUN-Stheno-3.2-v1.4-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 HOTHUN Stheno 3.2 v1.4 use?
Hugging Face lists the license as cc-by-nc-4.0. 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_0 quantized file is 4.66 GB and requires about 6.2 GB of VRAM at 8k context, fitting within an 8 GB budget.
Does the model support English?
No, it has been fine‑tuned exclusively in Hungarian and has not been modified or further trained in English.
Is the model suitable for commercial use?
No, the cc‑by‑nc‑4.0 license prohibits commercial use.