---

license: apache-2.0

language:

• en

library_name: gguf

tags:

• qwen3.5
• multimodal
• vision
• gguf
• xortron
• uncensored
• image-text-to-text

base_model: spinochenza/Agent.Xortron

pipeline_tag: image-text-to-text

---

Agent.Xortron — GGUF

GGUF quantizations of spinochenza/Agent.Xortron, a Qwen3.5-based multimodal (vision + text) model fine-tuned for uncensored, conversational AI.

Model Details

| Property | Value |

|---|---|

| Base Architecture | Qwen3.5 (Qwen3_5ForConditionalGeneration) |

| Parameters | ~27B |

| Text Layers | 64 (hybrid linear + full attention) |

| Vision Encoder | 27-layer ViT, patch_size=16, temporal_patch_size=2 |

| Context Length | 262,144 tokens |

| Original Name | darkc0de/XORTRON.CriminalComputing.2026.27B.NEXT |

| License | Apache 2.0 |

Available Files

| File | Type | Size | Description |

|---|---|---|---|

| Agent.Xortron-f16.gguf | F16 (text) | 51 GB | Full-precision text model (float16) |

| mmproj-Agent.Xortron-bf16.gguf | mmproj BF16 | 889 MB | Vision projector for multimodal inference |

Pending (not yet uploaded)

• Agent.Xortron-Q6_K.gguf — 6-bit quantization of the text model (~22 GB estimated)

Usage

llama.cpp / llama-server

# Multimodal (vision + text) inference
llama-server \
  --hf-repo hotdogs/Agent.Xortron-GGUF \
  --hf-file Agent.Xortron-f16.gguf \
  --mmproj mmproj-Agent.Xortron-bf16.gguf \
  -c 8192 \
  --port 8080

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(
    model_path="Agent.Xortron-f16.gguf",
    mmproj="mmproj-Agent.Xortron-bf16.gguf",
    n_ctx=8192,
    n_gpu_layers=-1,  # offload all layers to GPU if available
)

Conversion Details

Converted from the original safetensors using llama.cpp convert_hf_to_gguf.py:

# Text model
python convert_hf_to_gguf.py ./Agent.Xortron \
  --outtype f16 \
  --outfile Agent.Xortron-f16.gguf

# Vision projector (mmproj)
python convert_hf_to_gguf.py ./Agent.Xortron \
  --mmproj --outtype bf16 \
  --outfile mmproj-Agent.Xortron-bf16.gguf

Source

• Original Model: spinochenza/Agent.Xortron
• Conversion Tool: llama.cpp
• GGUF Format: ggml.org/docs/gguf

---

💖 Support / สนับสนุน

If you find this model useful, please consider supporting my work!

หากคุณคิดว่าโมเดลนี้มีประโยชน์ กรุณาสนับสนุนผลงานของฉันด้วยนะคะ! 🙏


₿ Bitcoin — BTC:

bc1qf27cyk3vmugcdyv9xdtuv5jwz37863crpj5c9v

Thank you for your support! 🙏✨

ขอบคุณมากๆ สำหรับการสนับสนุนค่า! 💖🤗