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 / LAPTOP-BENCHMARK-MATRIX.json

oktayd

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

a668ea0 verified 19 days ago

Raw

History Blame Contribute Delete

2.78 kB

	{
	"schema_version": "q36.laptop-matrix.v1",
	"status": "planned_not_executed",
	"quants": [
	"IQ4_XS",
	"Q3_K_M",
	"IQ2_M",
	"IQ1_M"
	],
	"backends": [
	"llama.cpp",
	"Ollama"
	],
	"runtime_profiles": [
	"stock",
	"optimized"
	],
	"primary_model": "Q36-v2 (same weights formerly released as v1.3)",
	"baseline_models": [
	"Huihui original",
	"Qwen/Qwen3.8-27B"
	],
	"primary_cells": 16,
	"potential_all_model_cells": 48,
	"baseline_quant_availability": "not_verified_do_not_substitute_different_quants_silently",
	"gpu_jobs_authorized": false,
	"downloads_started": false,
	"profiles": {
	"stock": "Backend defaults explicitly recorded, with same context, prompt, output and time budgets enforced. Not an undocumented historical server setup.",
	"optimized": "Tune CPU threads, batch sizes, GPU offload and supported KV cache/flash-attention on a disjoint tuning set; freeze per device/quant/backend before test. Never optimize on scored prompts."
	},
	"common_controls": [
	"Exact weights SHA256 and projector SHA256",
	"One immutable prompt/image manifest and renderer-specific chat-template capture",
	"Separate non-thinking controlled track from publisher-recommended thinking track",
	"Same sampling, output cap, context, per-request deadline across comparable cells",
	"One warmup excluded; three text throughput repetitions; quality one trial except separately named pass@3 tests",
	"AC power, power mode, driver, runtime versions, thermals and throttling logged",
	"Randomized balanced cell order; cooldown after sustained thermal throttling",
	"No concurrent workloads; restart server between cells; clear/reuse caches explicitly",
	"Keep runtime profile independent from model identity (stock model vs stock runtime are different axes)"
	],
	"metrics": [
	"prompt eval tokens/s",
	"decode tokens/s",
	"end-to-end tokens/s for matched IDs and length bins",
	"first visible output seconds (client) and TTFT if native provided",
	"request p50/p95 and total wall time",
	"prompt/completion token counts and missing usage",
	"process CPU percent 100%=one logical core",
	"process RSS, private/anonymous bytes if available, system commit, page faults, swap",
	"VRAM, GPU utilization, power, temperature, thermal limits",
	"content score, protocol score, refusal review, timeout/truncation/loop flags"
	],
	"memory_policy": "Fail fast on insufficient memory; classify not runnable/OOM, not wrong answer. No model file size presented as total RAM need.",
	"cost_policy": "Preparation/API metadata/local analysis only; no inference provider, remote jobs or paid judge calls without separate authorization."
	}