RE

RedSage K SFT GRPO

RedsageGGUF by mradermacherUpdated 2026-10-01
Download on Hugging Face
Parameters8.2B
Context32K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

RedSage K SFT GRPO needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

8B cybersecurity model translating natural‑language requests into Kali/Linux commands

RedSage K SFT GRPO is an 8.2B‑parameter model fine‑tuned for cybersecurity tool use. It converts natural‑language queries into Kali/Linux commands using Group Relative Policy Optimization. The model supports 8,504 verified query‑command pairs across 1,642 sub‑tools.

Good at

  • Translating natural language to Kali commands
  • Fine‑tuned for cybersecurity tool use
  • Supports 8,504 verified query‑command pairs

Limits

  • No vision support
  • No license specified
  • Requires 8,192‑token context for evaluation

Best for

  • Kali/Linux command generation
  • Cybersecurity tool automation
  • Command‑line assistance

Who it’s for. Developers and security analysts needing precise command generation from natural language. The model is useful for automating Kali Linux workflows and testing tool usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ1_S2.1 GB 3.8 GB
Fits Get file →
IQ1_M2.3 GB 4.0 GB
Fits Get file →
IQ2_XXS2.5 GB 4.2 GB
Fits Get file →
IQ2_XS2.7 GB 4.4 GB
Fits Get file →
IQ2_S2.9 GB 4.6 GB
Fits Get file →
IQ2_M3.1 GB 4.8 GB
Fits Get file →
Q2_K_S3.1 GB 4.8 GB
Fits Get file →
Q2_K3.3 GB 5.0 GB
Fits Get file →
IQ3_XXS3.4 GB 5.1 GB
Fits Get file →
IQ3_XS3.6 GB 5.3 GB
Fits Get file →
Q3_K_S3.8 GB 5.5 GB
Fits Get file →
IQ3_S3.8 GB 5.5 GB
Fits Get file →
IQ3_M3.9 GB 5.6 GB
Fits Get file →
Q3_K_M4.1 GB 5.8 GB
Fits Get file →
Q3_K_L4.4 GB 6.1 GB
Fits Get file →
IQ4_XS4.6 GB 6.3 GB
Fits Get file →
Q4_04.8 GB 6.5 GB
Fits Get file →
IQ4_NL4.8 GB 6.5 GB
Fits Get file →
Q4_K_S4.8 GB 6.5 GB
Fits Get file →
Q4_K_M5.0 GB 6.7 GB
Fits Get file →
Q4_15.2 GB 7.0 GB
Fits Get file →
Q5_K_S5.7 GB 7.4 GB
Tight Get file →
Q5_K_M5.9 GB 7.6 GB
Tight Get file →
Q6_K6.7 GB 8.4 GB
Too big Get file →

For 8 GB VRAM, use IQ4_XS (4.56 GB file, ~6.3 GB memory) or Q4_0 (4.79 GB file, ~6.5 GB memory). If 12 GB VRAM is available, Q4_K_M (5.03 GB file, ~6.7 GB memory) offers higher quality. For 16 GB VRAM, Q5_K_M (5.85 GB file, ~7.6 GB memory) provides a balance of size and performance. Estimates are approximate.

What GPU do you need for RedSage K SFT GRPO?

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 IQ1_M (2.3 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.4 GB in use).

Which RedSage K SFT GRPO quant should you choose?

Q4_K_M is the usual starting point for RedSage K SFT GRPO: it balances file size and quality well. Here it is a 5.0 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architectureqwen3
Parameters8.2B
Layers36
Trained context32,768 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyRedsage
Downloads (HF)628
Last updated2026-10-01

Frequently asked questions about RedSage K SFT GRPO

How much VRAM does RedSage K SFT GRPO need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 RedSage K SFT GRPO on an 8 GB GPU?

Yes, with Q5_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RedSage K SFT GRPO GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB and 19 more.

What context length does RedSage K SFT GRPO support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download RedSage K SFT GRPO GGUF?

The files are on Hugging Face in the mradermacher/RedSage-K-SFT-GRPO-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run RedSage K SFT GRPO on 8 GB VRAM?

Yes, use the IQ4_XS or Q4_0 quant, which require about 6.3–6.5 GB of VRAM at 8,192 context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length?

The model was trained with a context length of 32,768 tokens.

Other GGUFs of RedSage-K-SFT-GRPO

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Redsage models

All Redsage →

Other small models

All small models →