Instructions to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP with Transformers:

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

pipe = pipeline("image-text-to-text", model="AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP")
model = AutoModelForMultimodalLM.from_pretrained("AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP 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/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP: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 AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP: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 AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M

Use Docker

docker model run hf.co/AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M

LM Studio
Jan

vLLM

How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP"
# 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/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M

SGLang

How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP 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/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP" \
    --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/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP" \
        --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/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP with Ollama:
```
ollama run hf.co/AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M
```
Unsloth Desktop

How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M

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/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP with Docker Model Runner:
```
docker model run hf.co/AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M
```

Lemonade

How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP 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/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP: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 AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP: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 "AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP: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"

AMAImedia commited on 8 days ago

Commit

7b29da6

verified ·

1 Parent(s): 8f90cae

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -10

README.md CHANGED Viewed

@@ -16,8 +16,6 @@ tags:
 - 35B-A3B
 - Qwen3_6
 - Qwen3.6
-- Qwen3_5
-- Qwen3.5
 - Qwen3.6-35B-A3B
 language:
 - en
@@ -153,7 +151,7 @@ Good for imatrix and 0.6–35B-class work in RAM. <b>9B+ and searches need rente
 ## NOESIS / AMAImedia
 Released as part of the **NOESIS Professional Multilingual Dubbing Automation Platform**
-(framework: DHCF-FNO -- Deterministic Hybrid Control Framework for Frozen Neural Operators).
 - **Founder:** Ilia Bolotnikov
 - **Organization:** [AMAImedia.com](https://www.amaimedia.com)
@@ -298,8 +296,9 @@ Within each size group, **bold** denotes the best result and <u>underlining</u>
   </picture>
 </div>
-Across Claw-Eval, WildClawBench, AutomationBench, and GDPval, Occamy-1.0 lies near the low-cost knee of the empirical Pareto frontier. Relative to its Qwen3.6-35B-A3B starting checkpoint, it delivers a large aggregate capability gain with only a modest change in measured per-task inference cost. Benchmark scores are equally weighted after per-benchmark min-max normalization, and costs are macro-averaged per task under the frozen pricing protocol used in the report.
 ## 4. Training Recipe
@@ -311,7 +310,8 @@ Qwen3.6-35B-A3B
   └─ Sprint Expert: SFT          ├─ Uniform merge → SAO → Occamy-1.0
 ```
-The Marathon Expert learns sustained execution and accuracy-conditioned efficiency, while the Sprint Expert preserves broader agentic capability. A uniform parameter-space merge combines both experts into one checkpoint with no inference-time routing or ensembling, and a final Single-Rollout Asynchronous Optimization (SAO) stage refines the merged policy on a broad co-work mixture.
 The deduplicated SFT union across both experts is:
@@ -323,7 +323,8 @@ The deduplicated SFT union across both experts is:
 | Tool-call grounding | 7,429 | 9.1K | 67.7M |
 | **Overall** | **14,998** | **26.9K** | **403.3M** |
-Training tasks are grounded in executable environments with observable state transitions and task-level grading. The open-source [Dressage](https://github.com/Accio-Lab/Dressage) stack provides multi-harness execution, token-exact trajectory capture, sandbox integration, and multi-segment conversion for reinforcement learning.
 ## 5. Deployment
@@ -391,17 +392,22 @@ response = client.chat.completions.create(
 print(response.choices[0].message.content)
 ```
-For multi-turn agent runs, retain the complete assistant message returned by the server, including reasoning content and tool calls, then append tool results using the standard OpenAI chat-completions schema. This preserves the execution context that Occamy relies on across long workflows.
 ### Agent Frameworks
-Occamy was trained and evaluated across multiple harnesses, including [OpenClaw](https://github.com/openclaw/openclaw), [Hermes Agent](https://github.com/NousResearch/hermes-agent), and Accio Work. It can be integrated with other tool-using agent frameworks through the same OpenAI-compatible API.
 ---
 ## 7. License
-This repository is released under the [Apache License 2.0](LICENSE). See the Hugging Face model card for the terms that apply to the model weights.
 ---

 - 35B-A3B
 - Qwen3_6
 - Qwen3.6
 - Qwen3.6-35B-A3B
 language:
 - en
 ## NOESIS / AMAImedia
 Released as part of the **NOESIS Professional Multilingual Dubbing Automation Platform**
+(framework: Deterministic Hybrid Control Framework for Frozen Neural Operators - DHCF-FNO).
 - **Founder:** Ilia Bolotnikov
 - **Organization:** [AMAImedia.com](https://www.amaimedia.com)
   </picture>
 </div>
+Across Claw-Eval, WildClawBench, AutomationBench, and GDPval, Occamy-1.0 lies near the low-cost knee of the empirical Pareto frontier.
+Relative to its Qwen3.6-35B-A3B starting checkpoint, it delivers a large aggregate capability gain with only a modest change in measured per-task inference cost.
+Benchmark scores are equally weighted after per-benchmark min-max normalization, and costs are macro-averaged per task under the frozen pricing protocol used in the report.
 ## 4. Training Recipe
   └─ Sprint Expert: SFT          ├─ Uniform merge → SAO → Occamy-1.0
 ```
+The Marathon Expert learns sustained execution and accuracy-conditioned efficiency, while the Sprint Expert preserves broader agentic capability.
+A uniform parameter-space merge combines both experts into one checkpoint with no inference-time routing or ensembling, and a final Single-Rollout Asynchronous Optimization (SAO) stage refines the merged policy on a broad co-work mixture.
 The deduplicated SFT union across both experts is:
 | Tool-call grounding | 7,429 | 9.1K | 67.7M |
 | **Overall** | **14,998** | **26.9K** | **403.3M** |
+Training tasks are grounded in executable environments with observable state transitions and task-level grading.
+The open-source [Dressage](https://github.com/Accio-Lab/Dressage) stack provides multi-harness execution, token-exact trajectory capture, sandbox integration, and multi-segment conversion for reinforcement learning.
 ## 5. Deployment
 print(response.choices[0].message.content)
 ```
+For multi-turn agent runs, retain the complete assistant message returned by the server,
+including reasoning content and tool calls, then append tool results using the standard OpenAI chat-completions schema.
+This preserves the execution context that Occamy relies on across long workflows.
 ### Agent Frameworks
+Occamy was trained and evaluated across multiple harnesses,
+including [OpenClaw](https://github.com/openclaw/openclaw), [Hermes Agent](https://github.com/NousResearch/hermes-agent), and Accio Work.
+It can be integrated with other tool-using agent frameworks through the same OpenAI-compatible API.
 ---
 ## 7. License
+This repository is released under the [Apache License 2.0](LICENSE).
+See the Hugging Face model card for the terms that apply to the model weights.
 ---