M.O.G.-SEC-27B-1M-CTX needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 3.9 GB (BF16) to 29.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
M.O.G.-SEC-27B-1M-CTX – a 27B cybersec model with 1M token context
M.O.G.-SEC-27B-1M-CTX is a 27.3B dense hybrid fine‑tuned on modern offensive and defensive cybersecurity work. It offers a one‑million‑token context window via YaRN and supports reasoning, tools, and vision. The model is released under Apache‑2.0.
Good at
- Cybersecurity reasoning
- Tool‑enabled queries
- Vision‑aware analysis
Limits
- No moralization or refusal
- Requires large VRAM for 1M context
- No consumer chatbot use
Best for
- Red‑team planning
- Blue‑team threat hunting
- Security report generation
Who it’s for. Engineers, security analysts, and red‑team operators who need deep, in‑context cybersec reasoning without policy constraints. The model is not intended for general consumer use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 3.9 GB | 6.5 GB | Fits | Get file → | |
| Q2_K | 10.9 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_S | 12.3 GB | 14.9 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_L | 14.6 GB | 17.2 GB | Too big | Get file → | |
| Q4_K_S | 15.8 GB | 18.5 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q5_K_S | 19.0 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 22.2 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → | |
| Q8_0 | 29.0 GB | 31.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 19.5 GB at 8K context) or Q4_K_S (18.5 GB). For 12 GB VRAM, Q5_K_S (21.7 GB) or Q5_K_M (22.2 GB) are suitable. BF16 requires 6.5 GB at 8K context but needs more VRAM for 1M context.
What GPU do you need for M.O.G.-SEC-27B-1M-CTX?
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 BF16 (3.9 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (3.9 GB file, about 6.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_S (12.3 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
Which M.O.G.-SEC-27B-1M-CTX quant should you choose?
Q4_K_M is the usual starting point for M.O.G.-SEC-27B-1M-CTX: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 29.0 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.
If memory is tight, the smallest file is BF16 at 3.9 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about M.O.G.-SEC-27B-1M-CTX
How much VRAM does M.O.G.-SEC-27B-1M-CTX need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 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 M.O.G.-SEC-27B-1M-CTX on an 8 GB GPU?
Yes, with BF16: the 3.9 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 M.O.G.-SEC-27B-1M-CTX GGUF?
It depends on the quant: BF16 is 3.9 GB, Q2_K is 10.9 GB, Q3_K_S is 12.3 GB, Q3_K_M is 13.5 GB, Q3_K_L is 14.6 GB, Q4_K_S is 15.8 GB and 5 more.
What context length does M.O.G.-SEC-27B-1M-CTX support?
The GGUF header lists a trained context length of 1,000,000 tokens (977K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download M.O.G.-SEC-27B-1M-CTX GGUF?
The files are on Hugging Face in the Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX-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 M.O.G.-SEC-27B-1M-CTX 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 this model on 8 GB VRAM?
Use Q4_K_M or Q4_K_S quantizations; they estimate 19.5 GB and 18.5 GB at 8K context, so 8 GB is insufficient for full 1M context.
Does the model support vision?
Yes, it includes a native vision projector path.
Is the model free to use?
It is released under the Apache‑2.0 license, which allows free use with attribution.