Instructions to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF")
model = AutoModelForCausalLM.from_pretrained("AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-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 AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

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 AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

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 AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

Use Docker

docker model run hf.co/AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

LM Studio
Jan

vLLM

How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-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": "AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

SGLang

How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with Ollama:
```
ollama run hf.co/AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16
```
Unsloth Desktop

How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

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": "AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with Docker Model Runner:
```
docker model run hf.co/AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16
```

Lemonade

How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-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 AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

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 AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16

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 "AMAImedia/Qwen3.5-9B-NeoHorse1-Heretic-NOESIS-BF16-GGUF:F16" \
  --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"

NOESIS / AMAImedia

Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform.

Founder: Ilia Bolotnikov
Organization: AMAImedia.com
X (Twitter): @AMAImediacom
LinkedIn: Ilia Bolotnikov
Telegram: @djbionicl
Release date: 2026-09-09

This is a decensored version of a model, made using Heretic v1.4.0

Abliteration parameters

Parameter	Value
direction_index	16.33
attn.o_proj.max_weight	1.48
attn.o_proj.max_weight_position	19.08
attn.o_proj.min_weight	1.46
attn.o_proj.min_weight_distance	16.49
mlp.down_proj.max_weight	1.44
mlp.down_proj.max_weight_position	18.83
mlp.down_proj.min_weight	1.43
mlp.down_proj.min_weight_distance	13.39

Performance

Metric	This model	Original model (a model)
KL divergence	0.0181	0 (by definition)
Refusals	18/100	97/100

NeoHorse-1-9B

Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

Technical Report

NeoHorse-1-9B is a 9B causal language model and an initial prototype on the path toward recursive self-improvement (RSI). It is post-trained from Qwen3.5-9B for text-based agent harnesses, tool use, coding, and instruction following.

Derived from Qwen/Qwen3.5-9B and fine-tuned by TokenRhythm. This release contains language-model weights only and is repackaged for text-only inference. Vision weights are not included. Repackaging changes configuration and tensor key names, without changing the fine-tuned tensor values.

Highlights

Path toward RSI: the routing harness assigns tasks to a heterogeneous model pool, records tool interactions and outcomes, estimates capability demand, and uses capability-level feedback to shape the next training mixture. Updated models can return to the harness, closing a prototype evaluation–selection–update loop; extending this loop across successive iterations is the next step toward RSI.
Agentic post-training framework: the associated research explores routing-guided curriculum SFT and routing-guided on-policy distillation to turn execution trajectories into training signal while preserving execution and harness context around each response.
Data quality: exact and near-duplicate removal, evaluation decontamination, structural validation, six-dimensional semantic evaluation, and subscene-level Scene/Goal/Outcome labeling.
Broad gains: 69.04 macro average across ten benchmarks versus 65.60 for Qwen3.5-9B (+3.44).

Model Details

Property	Value
Model family	NeoHorse Agent-Native Causal Language Model
Parameters	Approximately 9B
Base model	Qwen3.5-9B
Post-training	Routing-guided agentic post-training
Interface	Text input and text output
Context length	262,144 natively and extensible up to 1,010,000 tokens.
Weight format / precision	Safetensors / BF16

Evaluation

The 9B track compares NeoHorse-1-9B with five representative open-weight baselines: Granite-4.2-8B, Qwen3.5-9B, Ornith-1.5-9B, Gemma-4-12B-it, and Muse-Glimmer-30B. Results cover ten benchmarks and are grouped by capability. Higher is better; Δ is NeoHorse-1-9B minus Qwen3.5-9B. Bold and underline mark the best and second-best results in each benchmark row, respectively; ties share the same formatting.

Benchmark	Granite-4.2-8B	Qwen3.5-9B	Ornith-1.5-9B	Gemma-4-12B-it	Muse-Glimmer-30B	NeoHorse-1-9B	Δ vs Qwen3.5-9B
🤖 Agentic
QwenClawBench	37.01	44.04	47.27	43.53	46.11	48.73	+4.69
WorkBuddy Bench	35.07	39.60	29.29	29.65	45.85	40.15	+0.55
PinchBench	56.93	74.55	68.22	58.89	71.35	82.25	+7.70
VitaBench	23.00	31.25	26.75	36.50	48.50	42.25	+11.00
BFCL v4	52.06	64.88	65.03	62.06	53.74	67.43	+2.55
tau2-Bench	62.28	88.04	83.68	59.37	76.64	90.82	+2.78
💻 Coding
HumanEval	96.34	92.68	93.90	100.00	98.17	98.17	+5.49
LiveCodeBench v6	72.00	65.14	47.43	73.14	65.71	65.14	+0.00
📚 Instruction Following
IFBench	78.00	66.33	40.00	77.67	78.67	66.33	+0.00
IFEval	92.98	89.46	71.35	94.27	93.90	89.09	-0.37
📊 Overall
Ten-benchmark average	60.57	65.60	57.29	63.51	67.86	69.04	+3.44

Reported protocol: SGLang v0.5.17 · temperature=1.0 · top_p=0.95 · top_k=20 · min_p=0.0 · presence_penalty=1.5 · repetition_penalty=1.0 · thinking mode enabled with enable_thinking=true and force_nonempty_content=true. QwenClawBench, WorkBuddy Bench, and tau2-Bench use three runs; PinchBench and VitaBench use one run; the remaining benchmarks follow their official protocols. VitaBench uses the DeepSeek-V4-Flash simulator and judge.

Deployment

The examples below are for self-hosted deployment from a downloaded local checkpoint.

Local checkpoint path

The examples below assume the checkpoint has already been downloaded to local disk. Set MODEL_PATH to the directory containing config.json, tokenizer files, and model weights.

MODEL_PATH="/path/to/NeoHorse-1-9B"

The OpenAI-compatible requests below use the server's --served-model-name (for example, neohorse-1-9b), not the filesystem path.

SGLang

The technical report uses SGLang v0.5.17.

pip install "sglang==0.5.17"
MODEL_PATH="/path/to/NeoHorse-1-9B"
python3 -m sglang.launch_server \
  --model-path "$MODEL_PATH" \
  --served-model-name neohorse-1-9b \
  --host 0.0.0.0 \
  --port 30000 \
  --context-length 262144 \
  --reasoning-parser qwen3 \
  --tool-call-parser qwen3_coder

Send an OpenAI-compatible request after the server starts:

curl http://localhost:30000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"neohorse-1-9b","messages":[{"role":"user","content":"Write a Python function that returns the first n Fibonacci numbers."}],"max_tokens":512}'

vLLM

pip install -U vllm
MODEL_PATH="/path/to/NeoHorse-1-9B"
vllm serve "$MODEL_PATH" \
  --served-model-name neohorse-1-9b \
  --host 0.0.0.0 \
  --port 8000 \
  --max-model-len 262144 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder

The server exposes an OpenAI-compatible /v1/chat/completions endpoint. Send a request after the server starts:

curl http://localhost:8000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"neohorse-1-9b","messages":[{"role":"user","content":"Write a Python function that returns the first n Fibonacci numbers."}],"max_tokens":512}'

The example uses the configured 262,144-token context limit. Actual capacity depends on GPU memory and serving settings; reduce the context limit if needed. These launch examples have not yet been validated on GPU for this repackaged release.

License

NeoHorse-1-9B is released under the Apache License 2.0.

The upstream model is Qwen/Qwen3.5-9B. Its original copyright notice, Copyright 2026 Alibaba Cloud, is retained in the license file. TokenRhythm has modified the model through fine-tuning and repackaging for text-only inference. Modification notices are included in this model card and the released configuration, weight index, and Safetensors metadata.

Citation

@misc{neohorse2026,
  title        = {NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness},
  author       = {NeoHorse Team},
  year         = {2026},
  howpublished = {arXiv preprint}
}

For questions or issue reports, use the NeoHorse project repository.