---

language:

• en

base_model:

• DarkKitsune/qwen3.5-9b-qworus

base_model_relation: quantized

library_name: llama.cpp

pipeline_tag: text-generation

tags:

• gguf
• quantized
• qwen3.5
• uncensored
• agent
• coding
• code
• ornith
• qwythos
• reasoning
• long-context
• tool-use

---

qwen3.5-9b-qworus-Q5_K_L-imat-GGUF

GGUF quantization of my merge qwen3.5-9b coding model DarkKitsune/qwen3.5-9b-qworus to Q5_K_L with importance matrices. Quantized using Q8_0 for token embedding and output weights, BF16 for ssm_alpha and ssm_beta weights, Q8_0 for ssm_out weights, and the default llama.cpp Q5_K_M config for all other weights.

Provides higher precision than Q5_K_M to help with long context work with reasoning and tool calls.

This model is also uncensored, due to the fact that both source models in the merge were already uncensored as well.

---

Original Model Card Below:

---

qwen3.5-9b-qworus

60/40 DARE-TIES of empero-ai/Qwythos-9B-v2 and PeppX/Ornith-1.0-9B-Uncensored. This merge exists because I find Qwythos to be excellent for its genuine stability and its ability to bug fix based on stderr output, but Ornith is better in its ability to set up a well-organized project with scalability in mind. So my goal is to cleanly combine the abilities of both.

Both source models are decensored, so this merge is decensored by default as well. It may inherit Qwythos' 1M context support due to using it as the base model, but I don't have the resources to actually test 1M tokens. The MTP head is also most likely not retained.

This model is for testing, and not intended to be used for any serious projects.

---

Mergekit

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: empero-ai/Qwythos-9B-v2

models:
  - model: empero-ai/Qwythos-9B-v2
    parameters:
      weight: 0.6
      density: 0.53

  - model: PeppX/Ornith-1.0-9B-Uncensored
    parameters:
      weight: 0.4
      density: 0.53

parameters:
  normalize: true
  int8_mask: true

dtype: bfloat16