Ornstein Hermes 3.6 27B SABER needs about 15.2 GB of memory at IQ3_M (a 12.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 16 quants, from 9.4 GB (IQ2_S) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Ornstein Hermes 3.6 27B SABER – a 27B Qwen35 model with controlled refusal shaping
Ornstein Hermes 3.6 27B SABER is a 26.9B parameter Qwen35 model quantized into GGUF. It supports reasoning, tools, and vision. The model is tuned to reduce over‑refusal while maintaining normal behavior.
Good at
- Reasoning
- Tool use
- Vision
Limits
- No vision support on low‑VRAM setups
- Large context requires high memory
- License is other
Best for
- Chat‑style interactions
- Tool‑augmented workflows
- Vision‑enabled tasks
Who it’s for. Users needing a local LLM that balances refusal control with general capability. Suitable for developers building chat or tool‑integrated applications on desktop hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_S | 9.4 GB | 12.0 GB | Too big | Get file → | |
| Q2_K_S | 10.2 GB | 12.9 GB | Too big | Get file → | |
| Q2_K | 10.7 GB | 13.4 GB | Too big | Get file → | |
| IQ3_XXS | 11.2 GB | 13.8 GB | Too big | Get file → | |
| IQ3_XS | 12.0 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_S | 12.1 GB | 14.7 GB | Too big | Get file → | |
| IQ3_S | 12.4 GB | 15.1 GB | Too big | Get file → | |
| IQ3_M | 12.6 GB | 15.2 GB | Too big | Get file → | |
| Q3_K_L | 14.3 GB | 17.0 GB | Too big | Get file → | |
| Q4_0 | 15.5 GB | 18.2 GB | Too big | Get file → | |
| Q4_K_S | 15.6 GB | 18.2 GB | Too big | Get file → | |
| IQ4_NL | 15.8 GB | 18.4 GB | Too big | Get file → | |
| Q4_1 | 17.1 GB | 19.7 GB | Too big | Get file → | |
| Q5_K_S | 18.7 GB | 21.3 GB | Too big | Get file → | |
| Q5_0 | 18.7 GB | 21.4 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_S (file size 9.36 GB, memory 12 GB at 8 k context). If you have 12 GB VRAM, Q2_K_S (10.25 GB, 12.9 GB) or Q2_K (10.71 GB, 13.4 GB) are good options. For higher quality on 16 GB VRAM, Q4_0 (15.52 GB, 18.2 GB) or Q4_K_S (15.59 GB, 18.2 GB) are recommended.
What GPU do you need for Ornstein Hermes 3.6 27B SABER?
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 IQ2_S (9.4 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (12.6 GB file, about 15.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_0 (18.7 GB file, about 21.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
Which Ornstein Hermes 3.6 27B SABER quant should you choose?
IQ3_M (12.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ2_S at 9.4 GB, with the quality trade-offs that come with fewer bits. 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornstein Hermes 3.6 27B SABER
How much VRAM does Ornstein Hermes 3.6 27B SABER need?
About 15.2 GB at IQ3_M with an 8K context window. That is the 12.6 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 Ornstein Hermes 3.6 27B SABER on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornstein Hermes 3.6 27B SABER GGUF?
It depends on the quant: IQ2_S is 9.4 GB, Q2_K_S is 10.2 GB, Q2_K is 10.7 GB, IQ3_XXS is 11.2 GB, IQ3_XS is 12.0 GB, Q3_K_S is 12.1 GB and 10 more.
What context length does Ornstein Hermes 3.6 27B SABER support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Ornstein Hermes 3.6 27B SABER GGUF?
The files are on Hugging Face in the gkraker04/Ornstein-Hermes-3.6-27B-SABER repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Ornstein Hermes 3.6 27B SABER use?
Hugging Face lists the license as other. 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 Ornstein Hermes 3.6 27B SABER on 8 GB VRAM?
Use the IQ2_S quantization; it requires about 12 GB of memory at 8 k context, which fits within 8 GB VRAM when using efficient batching.
Does this model support vision tasks?
Yes, the model has vision capabilities, but they may need additional GPU memory and a compatible frontend.
What is the recommended quant for a high‑quality local run?
Use Q4_0 or Q4_K_S; they provide near‑lossless quality with 15.52 GB or 15.59 GB file size and 18.2 GB memory at 8 k context.