Hy3 heretic i1 needs about 86.8 GB of memory at IQ2_XXS (a 77.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 0.6 GB to 96.0 GB (IQ2_M).
Hy3 heretic i1 – 295B‑parameter GGUF model
Hy3 heretic i1 is a 295B‑parameter model from the Heretic family. It is available in multiple quantizations and is licensed under apache‑2.0. The model is designed for general‑purpose language tasks and can be run with llama.cpp.
Good at
- Large‑scale reasoning
- Agentic task support
- Long‑context handling
Limits
- No vision support
- Requires large VRAM for high‑quality quants
- No explicit language list
Best for
- Coding assistance
- Productivity workflows
- Frontend development
Who it’s for. Developers and researchers needing a large‑parameter model for text‑only applications. The model is suitable for users with sufficient GPU memory to run the desired quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.6 GB | 1.2 GB | Fits | Get file → | |
| IQ1_S | 59.3 GB | 66.9 GB | Too big | Get file → | |
| IQ1_M | 66.0 GB | 74.4 GB | Too big | Get file → | |
| IQ2_XXS | 77.1 GB | 86.8 GB | Too big | Get file → | |
| IQ2_XS | 86.1 GB | 96.9 GB | Too big | Get file → | |
| IQ2_S | 87.1 GB | 98.1 GB | Too big | Get file → | |
| IQ2_M | 96.0 GB | 108.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (59.28 GB file, 66.9 GB memory at 8k context). For 16 GB VRAM, IQ1_M (65.96 GB file, 74.4 GB memory). For 24 GB VRAM, IQ2_XXS (77.08 GB file, 86.8 GB memory). Memory estimates are approximate.
What GPU do you need for Hy3 heretic i1?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
Which Hy3 heretic i1 quant should you choose?
IQ2_XXS (77.1 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is the first one in the table at 0.6 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hy3 heretic i1
How much VRAM does Hy3 heretic i1 need?
About 86.8 GB at IQ2_XXS with an 8K context window. That is the 77.1 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 Hy3 heretic i1 on an 8 GB GPU?
Yes, with the smaller files: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hy3 heretic i1 GGUF?
It depends on the quant: file is 0.6 GB, IQ1_S is 59.3 GB, IQ1_M is 66.0 GB, IQ2_XXS is 77.1 GB, IQ2_XS is 86.1 GB, IQ2_S is 87.1 GB and 1 more.
Where can I download Hy3 heretic i1 GGUF?
The files are on Hugging Face in the mradermacher/Hy3-heretic-i1-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 Hy3 heretic i1 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 Hy3 heretic i1 on 8 GB VRAM?
Use the IQ1_S quant; it requires about 66.9 GB memory at 8k context, which exceeds 8 GB VRAM, so it is not feasible.
Does Hy3 heretic i1 support vision tasks?
No, the model does not include vision capabilities.