Blackfrost-AI/CYBER-FROST-3.8-BF16 needs about 4.0 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 2.6 GB (Q4_K_M) to 123.1 GB (Q4_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
CYBER-FROST-3.8-BF16: 177B parameter security‑focused LLM with vision tower
CYBER-FROST-3.8-BF16 is a 177 billion‑parameter model built on the qwen4exp architecture. It includes a vision tower and is designed for security professionals. The model supports a 262144‑token context window and is available in multiple GGUF quantizations.
Good at
- Security‑centric analysis
- Vision‑enabled tasks
- Large context handling
Limits
- No validated multimodal quality
- License type "other"
- No official vision benchmark
Best for
- Red/blue/purple security workflows
- Vulnerable‑image analysis
- Token‑aware context management
Who it’s for. Developers and analysts in security research, assessment, engineering, and response who need a large‑context, vision‑capable LLM. The model is tailored for authorized, professional use cases.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.6 GB | 4.0 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 5.5 GB | Fits | Get file → | |
| Q2_K | 80.1 GB | 81.4 GB | Too big | Get file → | |
| Q2_K_S | 82.9 GB | 84.2 GB | Too big | Get file → | |
| Q3_K_M | 88.6 GB | 89.9 GB | Too big | Get file → | |
| Q3_K_S | 88.6 GB | 89.9 GB | Too big | Get file → | |
| MXFP4_MOE | 96.6 GB | 98.0 GB | Too big | Get file → | |
| Q4_K_M | 111.4 GB | 112.8 GB | Too big | Get file → | |
| IQ4_XS | 121.8 GB | 123.2 GB | Too big | Get file → | |
| Q4_K_XL | 123.1 GB | 124.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.63 GB, estimated 4 GB memory). For 16 GB VRAM, Q8_0 (4.13 GB, 5.5 GB memory) offers higher fidelity. Larger budgets can use Q4_K_M at 111.44 GB for maximum precision.
What GPU do you need for Blackfrost-AI/CYBER-FROST-3.8-BF16?
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: the best quant that fits is Q4_K_M (2.6 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.5 GB in use).
Which Blackfrost-AI/CYBER-FROST-3.8-BF16 quant should you choose?
Q4_K_M is the usual starting point for Blackfrost-AI/CYBER-FROST-3.8-BF16: it balances file size and quality well. Here it is a 2.6 GB file.
The Q8_0 file is 4.1 GB, about 1.6 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 Blackfrost-AI/CYBER-FROST-3.8-BF16
How much VRAM does Blackfrost-AI/CYBER-FROST-3.8-BF16 need?
About 4.0 GB at Q4_K_M with an 8K context window. That is the 2.6 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 Blackfrost-AI/CYBER-FROST-3.8-BF16 on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Blackfrost-AI/CYBER-FROST-3.8-BF16 GGUF?
It depends on the quant: Q4_K_M is 2.6 GB, Q8_0 is 4.1 GB, Q2_K is 80.1 GB, Q2_K_S is 82.9 GB, Q3_K_M is 88.6 GB, Q3_K_S is 88.6 GB and 4 more.
What context length does Blackfrost-AI/CYBER-FROST-3.8-BF16 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.3 GB at 32K.
Where can I download Blackfrost-AI/CYBER-FROST-3.8-BF16 GGUF?
The files are on Hugging Face in the freakyskittle/CYBER-FROST-3.8-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 Blackfrost-AI/CYBER-FROST-3.8-BF16 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 CYBER-FROST-3.8-BF16 on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 4 GB of VRAM at 8 k context, which fits within 8 GB. The larger Q8_0 quantization needs about 5.5 GB and also fits.
Does the model support vision tasks?
The model includes a vision tower, but it has not received a multimodal quality evaluation. Use with caution for vision workloads.
What context length does the model support?
The configured context length is 262144 tokens, but long‑context performance has not been tested.