Qwythos 9B v2 Heretic needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.6 GB (Q4_K_M) to 9.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Qwythos 9B v2 Heretic – a 8.95B Qwen3.5 hybrid model in GGUF format
Qwythos 9B v2 Heretic is an 8.95B parameter Qwen3.5 hybrid architecture model. It offers a 1,048,576 token context window and has had its safety alignment removed via Heretic. The model is available in multiple GGUF quantizations for llama.cpp and compatible runtimes.
Good at
- Large context reasoning
- Uncensored text generation
- Chain‑of‑thought support
Limits
- No vision or video capabilities
- Safety alignment removed – use responsibly
- Requires 8‑k context for memory estimates
Best for
- Long‑form text completion
- Complex reasoning tasks
- Custom fine‑tuning on text data
Who it’s for. Developers and researchers needing a large, uncensored Qwen3.5 model for text‑only workloads. The model is suitable for environments that support GGUF and can handle the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_M (5.63 GB file, 7.2 GB memory at 8‑k context). For 12‑GB VRAM, Q5_K_M (6.47 GB file, 8 GB memory) or Q6_K (7.36 GB file, 8.9 GB memory). Q8_0 (9.53 GB file, 11.1 GB memory) is best for 16‑GB or larger GPUs.
What GPU do you need for Qwythos 9B v2 Heretic?
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 Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
Which Qwythos 9B v2 Heretic quant should you choose?
Q4_K_M is the usual starting point for Qwythos 9B v2 Heretic: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 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 Qwythos 9B v2 Heretic
How much VRAM does Qwythos 9B v2 Heretic need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Qwythos 9B v2 Heretic on an 8 GB GPU?
Yes, with Q5_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwythos 9B v2 Heretic GGUF?
It depends on the quant: Q4_K_M is 5.6 GB, Q5_K_M is 6.5 GB, Q6_K is 7.4 GB, Q8_0 is 9.5 GB.
What context length does Qwythos 9B v2 Heretic support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). 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 Qwythos 9B v2 Heretic GGUF?
The files are on Hugging Face in the WaveCut/Qwythos-9B-v2-Heretic-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 Qwythos 9B v2 Heretic 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 Qwythos 9B v2 Heretic on 8 GB VRAM?
Yes, using the Q4_K_M quantization. It requires 7.2 GB of VRAM at 8‑k context, which fits within an 8‑GB budget with some headroom.
Does this model support vision or video input?
No. The model is text‑only; the original multimodal capabilities were removed in the Heretic pass.
What license applies to this model?
The model is released under the apache-2.0 license, allowing free use and modification.