Instructions to use jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Use Docker

docker model run hf.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

LM Studio
Jan
Ollama
How to use jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF with Ollama:
```
ollama run hf.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16
```
Unsloth Desktop

How to use jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF with Docker Model Runner:
```
docker model run hf.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16
```

Lemonade

How to use jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Run and chat with the model

lemonade run user.Qwen3.6-27B-AEON-RYS-15-20-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.6-27B-AEON-RYS-15-20-GGUF / README.md

jackasda211233

Link BF16 safetensors and GGUF artifacts in model card

c5fde11 verified 4 months ago

preview code

Raw

History Blame

7.41 kB

	---
	license: apache-2.0
	language:
	- en
	- zh
	- multilingual
	tags:
	- gguf
	- qwen3
	- qwen3.6
	- reasoning
	- coding
	- academic-writing
	- uncensored
	- rys
	base_model:
	- Qwen/Qwen3.6-27B
	---

	# Qwen3.6-27B-AEON-RYS-MaxThinkCoder-IQ4_NL GGUF

	Hyper-focused Q4NL RYS release for:
	- programming
	- technical reasoning
	- academic-style writing

	This release is built from:
	- AEON source model:
	`https://huggingface.co/AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored`

	Use this model with:
	- custom `ik-llama` fork, specialized and tuned for this exact model:
	`https://github.com/noonr48/qwen36-aeon-ik-llama`

	Side note (tool calling):
	some prompts can trigger repeated identical tool calls in one assistant turn (especially when the tool result is empty / slow).
	Update to the latest `ik-llama` fork version: it now deduplicates identical `tool_calls` server-side.

	## At a glance

	- released Q4_NL GGUF:
	[`Qwen3.6-27B-AEON-RYS-MaxThinkCoder-IQ4_NL-ik-llama-custom-mixed.gguf`](https://huggingface.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF/blob/main/Qwen3.6-27B-AEON-RYS-MaxThinkCoder-IQ4_NL-ik-llama-custom-mixed.gguf)
	- BF16 GGUF reference:
	[`Qwen3.6-27B-AEON-RYS-MaxThinkCoder-BF16.gguf`](https://huggingface.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF/blob/main/Qwen3.6-27B-AEON-RYS-MaxThinkCoder-BF16.gguf)
	- HF-format BF16 safetensors:
	[`bf16-safetensors/`](https://huggingface.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF/tree/main/bf16-safetensors)
	- intended runtime:
	custom `ik-llama`
	- compression:
	`54G` BF16 -> `16G` IQ4_NL
	- mixed validation snapshot:
	`0.7299` BF16 -> `0.7244` IQ4_NL
	- overall performance change:
	`-0.0055` absolute, about `-0.75%` relative
	- public codename:
	`MaxThinkCoder`
	- project focus:
	get as much capability as possible out of a Q4-class RYS model for hard English-first work
	- not a generic chat release
	- not a stock `llama.cpp` release



	## BF16 GGUF

	A BF16 GGUF is also included for people who want the unquantized GGUF-side artifact from the same released `15,20` RYS branch:

	[`Qwen3.6-27B-AEON-RYS-MaxThinkCoder-BF16.gguf`](https://huggingface.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF/blob/main/Qwen3.6-27B-AEON-RYS-MaxThinkCoder-BF16.gguf)

	Use this if you want a GGUF reference build, local conversion/testing, or to compare quantization behavior against the released `IQ4_NL` GGUF. For normal inference, the `IQ4_NL` file is the practical target. For Transformers/LoRA/SFT workflows, use the [`bf16-safetensors/`](https://huggingface.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF/tree/main/bf16-safetensors) folder instead.

	Size note:
	- BF16 GGUF: about `54G`
	- IQ4_NL GGUF: about `16G`

	## BF16 vs released custom IQ4_NL

	This is the critical compression result for the released custom `15,20` branch:
	- BF16 size:
	`54G`
	- released IQ4_NL size:
	`16G`
	- mixed 4-probe mean:
	`0.7299` BF16 -> `0.7244` IQ4_NL
	- net performance change:
	`-0.0055` absolute, about `-0.75%` relative

	Probe-level snapshot:

	\| probe \| BF16 \| IQ4_NL \|
	\|---\|---:\|---:\|
	\| `math_16` \| `0.8421` \| `0.7897` \|
	\| `eq_16` \| `0.7123` \| `0.7111` \|
	\| `math_4` \| `0.4851` \| `0.5170` \|
	\| `gsm8k_5` \| `0.8800` \| `0.8800` \|

	Practical read:
	- the released Q4 model is roughly `70%` smaller on disk
	- the mixed validation snapshot stayed under a `1%` overall drop
	- `eq_16` and `gsm8k_5` were effectively flat
	- `math_4` did not regress in this tiny probe
	- the real measurable hit was mostly on `math_16`

	## Speed snapshot

	Exact comparison hardware:
	- `6x NVIDIA GeForce RTX 5060 Ti`

	\| runtime \| tested file \| ctx \| np \| KV \| decode tok/s \| prompt tok/s \| note \|
	\|---\|---\|---:\|---:\|---\|---:\|---:\|---\|
	\| patched upstream-style `llama.cpp` \| same internal standard-typed comparison file \| `4096` \| `1` \| `f16` \| `22.51` \| `187.18` \| internal comparison only \|
	\| custom `ik-llama` fork \| released custom-mixed file \| `409600` \| `2` \| `f32/f32` \| `39.37` \| `164.98` \| actual deployment target \|

	## Why there is no `llama.cpp` file in this release

	We did build and benchmark an internal standard-typed comparison artifact.
	We are not releasing it as a public `llama.cpp` file.

	Why:
	- the main model this project is about is the custom mixed GGUF, which needs the forked `ik-llama` runtime
	- even the internal standard-typed path was only validated on a patched upstream-style `llama.cpp`, not clean stock mainline
	- since users would still need a special runtime path anyway, we did not think it was worth shipping a second public file that suggests plain stock `llama.cpp` support

	So the intended reading is simple:
	- this repo releases the `ik-llama`-targeted model
	- if you want plain stock `llama.cpp`, this is not that release

	## Hyper-focused project

	This was a deliberately narrow project.

	The target was not “best general chat model”.
	The target was:
	- strongest Q4-class English-first model we could get for coding, reasoning, and academic work
	- using the AEON uncensored branch as the source
	- using the custom `ik-llama` path because prior RYS experiments suggested that path preserved quality better than standard `llama.cpp`-style quantization

	## Imatrix calibration profile

	The quantization was deliberately biased toward reasoning and technical work.

	Heuristic calibration breakdown:
	- `math_reasoning`: `5,688` chunks, `1,706,070` chars (`36.0%`)
	- `code_technical`: `3,518` chunks, `1,343,392` chars (`28.4%`)
	- `experiment_docs`: `808` chunks, `224,169` chars (`4.7%`)
	- `writing_chat`: `387` chunks, `164,097` chars (`3.5%`)
	- `other`: `5,139` chunks, `1,249,396` chars (`26.4%`)

	Practical read:
	- heavy focus on reasoning math, code, technical prose, and experiment artifacts
	- very little emphasis on generic social chat

	## RYS choice

	This release came from the AEON-derived `15,20` RYS branch.
	That was the practical release target because it quantized cleanly and held up as the best balanced candidate for this experiment.

	## Use case

	Recommended:
	- coding
	- technical reasoning
	- academic-style writing
	- long-context English work

	Not recommended as a generic safe-default chat model.
	This branch came from an uncensored source path.


	## BF16 safetensors for fine-tuning

	The original HF-format BF16 checkpoint for the released `15,20` RYS branch is included here:

	[`bf16-safetensors/`](https://huggingface.co/jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF/tree/main/bf16-safetensors)

	Use the files in that folder for Transformers-based work such as LoRA, SFT, continued training, or conversion into another training format. Use the GGUF file in the repo root for `ik-llama` inference.

	Loading example:

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	repo_id = "jackasda211233/Qwen3.6-27B-AEON-RYS-15-20-GGUF"
	subfolder = "bf16-safetensors"

	tok = AutoTokenizer.from_pretrained(repo_id, subfolder=subfolder, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(
	repo_id,
	subfolder=subfolder,
	torch_dtype="bfloat16",
	device_map="auto",
	trust_remote_code=True,
	)
	```

	RYS note for anyone rebuilding or modifying this checkpoint: the config is part of the model. The BF16 folder keeps the corrected hybrid-stack metadata for the `15,20` insert, including `text_config.num_hidden_layers = 69` and a 69-entry `text_config.layer_types` list. Do not change the layer count without remapping `layer_types` to the same layer order as the tensors.