Not-For-All-Audiences

abliterated

heretic

uncensor

hermes-lineage

Model card Files Files and versions

xet

Community

Instructions to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT with Transformers:

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

pipe = pipeline("image-text-to-text", model="oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT")
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("oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT")
model = AutoModelForMultimodalLM.from_pretrained("oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT", 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

vLLM

How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT",
		"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/oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT

SGLang

How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT 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 "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT" \
    --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": "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT",
		"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 "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT" \
        --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": "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT with Docker Model Runner:
```
docker model run hf.co/oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT
```

Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT / BENCHMARK-EXTENSION-QWEN38.json

oktayd

Publish Q36 v2 naming, complete edition guide and honest benchmark scope

a668ea0 verified 24 days ago

Raw

History Blame Contribute Delete

11.6 kB

	{
	"schema_version": "q36.benchmark-extension.v1",
	"source_url": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"source_revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
	"status": "registered_not_run",
	"publication_scores_not_local_results": true,
	"new_model_baseline": {
	"id": "Qwen/Qwen3.8-27B",
	"revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
	"downloaded_weights": false,
	"measured_locally": false
	},
	"benchmarks": [
	{
	"name": "Terminal Bench 2.1 (Terminus)",
	"category": "coding",
	"publisher_reported": "73.0",
	"proposed_local_cases": 5,
	"environment": "terminal_container",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "version_and_harness_required",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "SWE-bench Pro",
	"category": "coding",
	"publisher_reported": "61.7",
	"proposed_local_cases": 5,
	"environment": "repository_container",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "refined_tasks_Claude_Code_256K_temp1_top_p095",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "NL2Repo-Bench",
	"category": "coding",
	"publisher_reported": "42.3",
	"proposed_local_cases": 5,
	"environment": "repository_container",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "Claude_Code_no_repository_download_reward_hacking",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "DeepSWE 1.1",
	"category": "coding",
	"publisher_reported": "42.2",
	"proposed_local_cases": 5,
	"environment": "repository_container",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "Claude_Code_256K_temp1_top_p095",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "QwenSWEBench",
	"category": "coding",
	"publisher_reported": "79.0",
	"proposed_local_cases": null,
	"environment": "in_house",
	"status": "blocked_in_house_release_needed",
	"requirements": "in_house_avg3_8h_timeout_32768_output_256K_context",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "CoWorkBench",
	"category": "agent",
	"publisher_reported": "70.7",
	"proposed_local_cases": null,
	"environment": "in_house",
	"status": "blocked_in_house_release_needed",
	"requirements": "in_house_productivity_tasks",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "JobBench",
	"category": "agent",
	"publisher_reported": "33.4",
	"proposed_local_cases": 5,
	"environment": "agent_environment",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "dataset_and_harness_availability_unverified",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "Agents' Last Exam",
	"category": "agent",
	"publisher_reported": "Pass@1 20.4; Score 42.9",
	"proposed_local_cases": 5,
	"environment": "agent_environment",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "two_distinct_metrics",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "IFBench",
	"category": "instruction",
	"publisher_reported": "79.5",
	"proposed_local_cases": 20,
	"environment": "text",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "not_IFEval",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "GPQA Diamond",
	"category": "science",
	"publisher_reported": "89.2",
	"proposed_local_cases": 20,
	"environment": "text",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "existing_5_prompt_diagnostic_not_full_benchmark",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "HLE",
	"category": "reasoning",
	"publisher_reported": "30.8",
	"proposed_local_cases": 10,
	"environment": "text_multimodal",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "publisher_GPT4o_judge_separate_judge_budget",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "LiveCodeBench v6",
	"category": "coding",
	"publisher_reported": "90.3",
	"proposed_local_cases": 10,
	"environment": "code_sandbox",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "existing_LiveCodeBench_revision_must_be_reconciled",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "OSWorld-Verified",
	"category": "desktop",
	"publisher_reported": "84.3",
	"proposed_local_cases": 5,
	"environment": "desktop_vm",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "real_actions_not_static_screenshot_qa",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "WebArena-Verified",
	"category": "browser",
	"publisher_reported": "64.8",
	"proposed_local_cases": 5,
	"environment": "browser_environment",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "official_grader_OSWorld_scaffold",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "AndroidWorld",
	"category": "mobile",
	"publisher_reported": "81.9",
	"proposed_local_cases": 5,
	"environment": "android_emulator",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "emulator_and_state_reset_required",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "RecreationBench",
	"category": "application",
	"publisher_reported": "47.1",
	"proposed_local_cases": null,
	"environment": "in_house",
	"status": "blocked_in_house_release_needed",
	"requirements": "in_house_Ubuntu_macOS_Windows_Android_web",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "ClawEval-MM",
	"category": "tools",
	"publisher_reported": "Pass@3 57.4; Average 56.9",
	"proposed_local_cases": 5,
	"environment": "multimodal_agent",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "official_pass3_requires_three_trials; local_single_trial_not_pass3",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "SWE-MM",
	"category": "coding_vision",
	"publisher_reported": "38.6",
	"proposed_local_cases": 5,
	"environment": "repository_container",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "public_dev_split_with_Opus47_appendix8_3_modifications",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "Vision2Web",
	"category": "web_development",
	"publisher_reported": "62.9",
	"proposed_local_cases": 5,
	"environment": "browser_and_code",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "Claude_Code_judged_gpt5.4_2026_03_05",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "MathVision",
	"category": "visual_reasoning",
	"publisher_reported": "Without CI 90.0; With CI 94.6",
	"proposed_local_cases": 10,
	"environment": "image_qa_plus_optional_code",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "corrected_annotations_boxed_final_CI_strata_separate",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "BabyVision",
	"category": "visual_reasoning",
	"publisher_reported": "Without CI 65.7; With CI 85.6",
	"proposed_local_cases": 10,
	"environment": "image_qa_plus_optional_code",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "CI_strata_separate",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "CharXiv (RQ)",
	"category": "chart_reasoning",
	"publisher_reported": "Without CI 83.7; With CI 90.2",
	"proposed_local_cases": 10,
	"environment": "image_qa_plus_optional_code",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "corrected_annotations_CI_strata_separate",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "OmniDocBench 1.5",
	"category": "document",
	"publisher_reported": "91.1",
	"proposed_local_cases": 10,
	"environment": "document_parser",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "official_metric_not_generic_accuracy",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "RealWorldQA",
	"category": "perception",
	"publisher_reported": "85.9",
	"proposed_local_cases": 20,
	"environment": "image_qa",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "dataset_revision_and_image_preprocessing_lock_required",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	},
	{
	"name": "ERQA",
	"category": "embodied_reasoning",
	"publisher_reported": "65.5",
	"proposed_local_cases": 10,
	"environment": "image_qa",
	"status": "registered_adapter_and_data_not_prepared",
	"requirements": "dataset_revision_and_official_scoring_required",
	"source": "https://huggingface.co/Qwen/Qwen3.8-27B",
	"repetitions": 1,
	"official_comparable": false
	}
	]
	}