Primus_Exploit_Finetune needs about 17.6 GB of memory at BF16 (a 16.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 8.5 GB (Q8_0) to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Primus_Exploit_Finetune – 8.03B Llama model fine‑tuned for exploit analysis
Primus_Exploit_Finetune is an 8.03B parameter Llama architecture model. It was trained on a 131072 token context window. The model is available in three GGUF quantizations.
Good at
- Exploit analysis
- Fine‑tuned Llama tasks
- Large context handling
Limits
- No license information
- No vision support
- Large VRAM requirement
Best for
- Security researchers analyzing code
- Exploit detection workflows
- LLM‑based vulnerability tools
Who it’s for. The model is intended for users who need a large‑context Llama model fine‑tuned for exploit‑related tasks. It is suitable for security analysts and developers building specialized LLM tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → | |
| BF16 | 16.1 GB | 17.6 GB | Too big | Get file → | |
| F16 | 16.1 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8_0 quant (8.54 GB file, ~10.1 GB VRAM). For 16 GB VRAM, BF16 or F16 quant (16.07 GB file, ~17.6 GB VRAM) are suitable. Memory estimates are approximate.
What GPU do you need for Primus_Exploit_Finetune?
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 Q8_0 (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 17.6 GB in use).
Which Primus_Exploit_Finetune quant should you choose?
BF16 (16.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q8_0 at 8.5 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Primus_Exploit_Finetune
How much VRAM does Primus_Exploit_Finetune need?
About 17.6 GB at BF16 with an 8K context window. That is the 16.1 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 Primus_Exploit_Finetune on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Primus_Exploit_Finetune GGUF?
It depends on the quant: Q8_0 is 8.5 GB, BF16 is 16.1 GB, F16 is 16.1 GB.
What context length does Primus_Exploit_Finetune support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Primus_Exploit_Finetune GGUF?
The files are on Hugging Face in the kygbjs/primus_exploit_finetune repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Primus_Exploit_Finetune on 8 GB VRAM?
Yes, the Q8_0 quant requires about 10.1 GB VRAM at 8 k context, which is close to 8 GB but may need lower context or swap.
What quantization should I use for 16 GB VRAM?
Use BF16 or F16 quant, each 16.07 GB file and ~17.6 GB VRAM at 8 k context.
Does the model support vision tasks?
No, the model has no vision support.