Instructions to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-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 vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-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 vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

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 vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

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 vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

Ollama
How to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF with Ollama:
```
ollama run hf.co/vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M
```

Unsloth Studio

How to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF to start chatting

How to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-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 vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

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 vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

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 "vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M" \
  --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"

Docker Model Runner
How to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M
```

Lemonade

How to use vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Ornith 1.0 35B AEON Ultimate Uncensored - GGUF

GGUF quantizations of AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16, produced from the BF16 source weights using importance-matrix calibration.

Two variants are provided: standard trunk (no MTP) and MTP-grafted (with Multi-Token Prediction block for speculative decoding).

Files

Standard Trunk (no MTP)

For standard autoregressive inference. Smaller files, no speculative decoding overhead.

File	Quant	Size	BPW	Target GPU
`ornith-aeon-35b-Q8_0.gguf`	Q8_0	35 GB	~8.5	48GB+ (near-lossless)
`ornith-aeon-35b-Q6_K.gguf`	Q6_K	27 GB	~6.6	32GB+ (high quality)
`ornith-aeon-35b-Q5_K_M.gguf`	Q5_K_M	24 GB	~5.7	24GB (quality-first)
`ornith-aeon-35b-Q4_K_M.gguf`	Q4_K_M	21.2 GB	~4.8	24GB (balanced)
`ornith-aeon-35b-Q4_K_S.gguf`	Q4_K_S	19.9 GB	~4.6	24GB fallback
`ornith-aeon-35b-IQ4_XS.gguf`	IQ4_XS	18.7 GB	~4.3	20GB (RTX 4000 Ada)
`ornith-aeon-35b-Q3_K_M.gguf`	Q3_K_M	16.8 GB	~3.9	16GB GPUs
`ornith-aeon-35b-Q2_K.gguf`	Q2_K	12.9 GB	~3.0	12GB GPUs
`ornith-aeon-35b-IQ1_M.gguf`	IQ1_M	8.2 GB	~1.8	8GB GPUs
`ornith-aeon-35b.imatrix`	-	184 MB	-	Importance matrix

MTP-Grafted (with Multi-Token Prediction)

These GGUFs contain all 785 MTP tensors grafted from the base Qwen/Qwen3.5-35B-A3B model, adding a full MTP prediction block (blk.40) with 256 MoE experts. Use with --spec-type draft-mtp for speculative decoding. MTP is bundled in the GGUF -- no separate draft file needed.

File	Quant	Size	BPW	Target GPU
`ornith-aeon-35b-MTP-Q8_0.gguf`	Q8_0	36 GB	~8.5	48GB+ (near-lossless)
`ornith-aeon-35b-MTP-Q6_K.gguf`	Q6_K	28 GB	~6.6	32GB+ (high quality)
`ornith-aeon-35b-MTP-Q5_K_M.gguf`	Q5_K_M	24 GB	~5.7	24GB (quality-first)
`ornith-aeon-35b-MTP-Q4_K_M.gguf`	Q4_K_M	21.7 GB	~4.8	24GB (balanced)
`ornith-aeon-35b-MTP-Q4_K_S.gguf`	Q4_K_S	20.4 GB	~4.6	24GB fallback
`ornith-aeon-35b-MTP-IQ4_XS.gguf`	IQ4_XS	19.2 GB	~4.3	20-24GB
`ornith-aeon-35b-MTP-Q3_K_M.gguf`	Q3_K_M	17.2 GB	~3.9	16GB GPUs
`ornith-aeon-35b-MTP-Q2_K.gguf`	Q2_K	13.3 GB	~3.0	12GB GPUs
`ornith-aeon-35b-MTP.imatrix`	-	184 MB	-	Importance matrix

Why Two Variants?

The original AEON fine-tune lost its 785 MTP weight tensors. HuggingFace Transformers' AutoModelForCausalLM silently drops all mtp.* tensors during loading (_keys_to_ignore_on_load_unexpected = [r"^mtp.*"]). The mtp_num_hidden_layers: 1 in config.json is orphaned metadata from the base Qwen3.5-35B-A3B model.

The MTP-grafted variants restore all 785 MTP tensors (~488 MB BF16) by copying them from the base Qwen3.5-35B-A3B model. This works because Ornith shares identical architecture, hidden dimensions, expert count, and embedding space with its base model. Community-measured acceptance rates for grafted MTP: 58-100%.

MTP Benchmark Results

Tested: MTP-Q4_K_M on DGX Spark (GB10)

Mode	Prompt	Generation
Standard (no MTP)	47.4 t/s	34.9 t/s
Embedded `--spec-type draft-mtp`	46.2 t/s	62.8 t/s

1.8x generation speedup with the bundled MTP head on a single GPU.

Embedded MTP vs separate draft model

An important distinction for MoE speculative decoding:

Embedded MTP head (bundled in the GGUF, --spec-type draft-mtp): Net positive. The MTP head shares the model's KV cache and embedding space. Measured +27-80% generation speedup depending on workload and hardware.
Separate draft model (-md with a standalone GGUF): Net negative for MoE. A separate draft model triggers expert-union overhead during batch verification -- more expert weight blocks must be read from VRAM, exceeding the savings. Benchmarks show -18% to -52% regression.

The MTP-grafted GGUFs in this repo use the embedded approach.

How to Run

Standard inference (recommended for most users)

llama-server \
  -m ornith-aeon-35b-Q4_K_M.gguf \
  -a ornith-aeon-35b \
  --host 0.0.0.0 --port 8083 \
  -ngl 99 \
  --n-cpu-moe 3 \
  -fa on \
  -ctk q4_0 -ctv q4_0 \
  -c 32768 \
  -b 2048 -ub 768 \
  -np 1 -cb \
  -n 16384 \
  --temp 0.6 --top-k 20 --top-p 0.95 \
  --repeat-penalty 1.1 \
  --jinja \
  --reasoning-format deepseek \
  --reasoning-budget 1024

With MTP speculative decoding (faster generation)

Requires llama.cpp built from latest master (b9606+). MTP is bundled in the GGUF -- no separate draft file needed.

llama-server \
  -m ornith-aeon-35b-MTP-Q4_K_M.gguf \
  -a ornith-aeon-35b \
  --spec-type draft-mtp \
  --host 0.0.0.0 --port 8083 \
  -ngl 99 \
  --n-cpu-moe 3 \
  -fa on \
  -ctk q4_0 -ctv q4_0 \
  -c 32768 \
  -b 2048 -ub 768 \
  --parallel 1 \
  --temp 0.6 --top-k 20 --top-p 0.95 \
  --repeat-penalty 1.1 \
  --jinja \
  --reasoning-format deepseek \
  --reasoning-budget 1024

RTX 4000 Ada 20GB

llama-server \
  -m ornith-aeon-35b-MTP-IQ4_XS.gguf \
  -a ornith-aeon-35b \
  --spec-type draft-mtp \
  --host 0.0.0.0 --port 8083 \
  -ngl 99 \
  --n-cpu-moe 5 \
  -fa on \
  -ctk q4_0 -ctv q4_0 \
  -c 8192 \
  -b 1024 -ub 512 \
  --parallel 1 \
  --temp 0.6 --top-k 20 --top-p 0.95 \
  --repeat-penalty 1.1 \
  --jinja \
  --reasoning-format deepseek \
  --reasoning-budget 1024

High quality on 32GB+ GPU

llama-server \
  -m ornith-aeon-35b-MTP-Q6_K.gguf \
  -a ornith-aeon-35b \
  --spec-type draft-mtp \
  --host 0.0.0.0 --port 8083 \
  -ngl 99 \
  -fa on \
  -ctk q8_0 -ctv q8_0 \
  -c 32768 \
  -b 2048 -ub 768 \
  --parallel 1 \
  --temp 0.6 --top-k 20 --top-p 0.95 \
  --repeat-penalty 1.1 \
  --jinja \
  --reasoning-format deepseek \
  --reasoning-budget 1024

Speculative Decoding Options

All available in llama.cpp latest master. Work on any CUDA GPU (Ada Lovelace, Ampere, Blackwell):

Strategy	Flag	Draft Model?	Notes
MTP (embedded)	`--spec-type draft-mtp`	Bundled in MTP GGUFs	Requires `--parallel 1`. Measured +80% on Spark.
Eagle3	`--spec-type draft-eagle3`	Separate GGUF	PR #18039. No pre-trained drafter for this model yet.
DFlash	`--spec-type draft-dflash`	Separate GGUF	z-lab/Qwen3.5-35B-A3B-DFlash. Best results on vLLM/SGLang at BF16/FP8.
N-gram	`--spec-default`	None	Zero VRAM cost. Marginal benefit on structured output.

Key Parameters

Parameter	Value	Why
`-ngl 99`	Offload all layers to GPU	Maximizes speed
`--spec-type draft-mtp`	MTP speculative decoding	Only with MTP-grafted GGUFs
`--parallel 1`	Single slot	Required for MTP
`--n-cpu-moe N`	Offload N MoE layers to CPU	Saves ~0.8GB per layer
`-fa on`	Flash attention	Reduces KV cache memory
`-ctk q4_0 -ctv q4_0`	Quantize KV cache	Saves ~60% KV cache VRAM
`--jinja`	Jinja2 chat template	Required for this model
`--reasoning-format deepseek`	Thinking mode	Model uses think tags

If It OOMs

Increase --n-cpu-moe (trades speed for VRAM)
Lower context: -c 8192 or -c 4096
Lower batch: -b 512 -ub 256
Use a trunk (non-MTP) file to save ~0.5-1GB
Use a smaller quant

Model Details

Architecture: Qwen3.5-MoE (Mixture of Experts)
Total Parameters: ~35B
Active Parameters per Token: ~9B (4 of 64 experts active)
MTP Tensors: 785 (grafted from base model in MTP variants)
Chat Template: ChatML
Thinking/Reasoning: DeepSeek-style think tags
Context: Up to 131K tokens (limited by available VRAM)

Quantization Details

Source: BF16 safetensors from AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16
MTP Graft Source: 785 mtp.* tensors from Qwen/Qwen3.5-35B-A3B (~488 MB BF16)
Importance Matrix: Calibrated on diverse coding, debugging, system design, and reasoning prompts
llama.cpp: Built from latest master (post-b9606, with MTP/Eagle3/DFlash support merged)
Platform: DGX Spark (aarch64, CUDA 13.0)

Credits

Base model by AEON-7
MTP weights from Qwen/Qwen3.5-35B-A3B
Quantization by vcruz305

Downloads last month: 34,977

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF

Base model

deepreinforce-ai/Ornith-1.0-35B

Finetuned

AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16

Quantized

(7)

this model