Not-For-All-Audiences

hermes-lineage

mtp

coding

tool-calling

reasoning

roleplay

imatrix

Model card Files Files and versions

xet

Community

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama 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 oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama: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 oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama: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 oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M

Use Docker

docker model run hf.co/oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M

LM Studio
Jan

vLLM

How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama 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-Llama"
# 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-Llama",
		"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-Llama:Q4_K_M

Ollama
How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama with Ollama:
```
ollama run hf.co/oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama: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": "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama with Docker Model Runner:
```
docker model run hf.co/oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama-Q4_K_M

List all available models

lemonade list

Hermes Agent

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama: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 oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama: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 "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama: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"

Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-Llama / BENCHMARK-FIXES-AND-RUNTIME-PROFILE.md

oktayd

Unify one-step runtime profile, personality, cache and loop guards

4fa3c78 verified 18 days ago

preview code

Raw

History Blame Contribute Delete

5.16 kB

Benchmark fixes that are now normal runtime policy

This document distinguishes a reproducible benchmark setting from the normal unattended operating policy. The one-step installer writes the complete profile, caches, loop guards, personality and system message together; no manual copy/paste of individual settings is required. Every general reliability finding below is applied in the normal profile at the user's selected context; the 9,600-token Q4_K_M setting is retained only to reproduce its local regression.

Normal policy

Non-thinking is the default: --reasoning off / enable_thinking=False.
Sampling is required: temperature 0.7, top_p 0.8, top_k 20, min_p 0; do not use greedy temperature 0 for normal Qwen non-thinking work.
Long-running services use --parallel 1, --n-predict 4096, --repeat-penalty 1.08, and --repeat-last-n 128. Clients must use a finite lower per-request maximum whenever possible.
For explicit identical-token repetition requests only, use a per-request repetition penalty of 1.0, then restore 1.08.
Treat exact text, JSON/schema, required counts and tool-call arguments as validator-backed output. At most three repairs may use the original request, rejected draft and deterministic validator feedback. A repair is operational reliability work, not a single-pass benchmark score.
Explicit math/reasoning requests may enable thinking with a finite output cap. Do not enable it in harnesses whose stop sequence can end a response inside hidden reasoning.
llama.cpp normal profile: 131072 context on the validated 32-GB-RAM / 8-GB-VRAM laptop, RAM-resident weights, q8_0 K/V cache, Flash Attention, continuous batching, a 1536-MiB GPU margin, --fit on, and bounded CPU/RAM cache settings. Lower context before changing quantization when a real workload exhausts memory.
The always-on system profile preserves the direct, sharp-witted, business-minded Q36 personality. It also contains the strict final-output compiler text and loop/repair rule. The supplied client wrapper and Hermes attach it on every command; Ollama embeds it in the created model. Raw llama.cpp HTTP clients must send it explicitly because the tested llama-server build has no server-global system-prompt flag.

The machine-readable version is configs/q36-reliability-profile.v1.json. The Windows installer creates the same profile and launcher.

What the local regressions found

Area	Limited local observation	Fix used in normal operation
Exact format constraints / IFBench	Greedy or unvalidated output missed mechanical constraints. The fixed 20-row regression accepted 20/20 prompt constraints and 22/22 instruction constraints after bounded validation.	Sampling defaults plus strict final-output prompt and bounded validator repair for machine-sensitive tasks.
GSM8K-style explicit reasoning	On the fixed 20-row slice, non-thinking scored 13/20; thinking with a 1,024-token cap scored 17/20.	Non-thinking remains default; an explicit reasoning task may opt into thinking and a finite cap.
BBH Boolean Expressions with CoT	On the fixed 20-row slice, thinking interacted badly with the task's double-newline stop and produced 6 invalid terminations; non-thinking scored 18/20.	Keep non-thinking for ordinary work and for stop-sensitive harnesses.
Agentic MBPP repair	A network-isolated, visible-test repair loop reached 4/5 on a five-task public sample; extra thinking and additional repairs did not reliably improve it.	Tool/code workflows use visible validation, preserve failed tests, and stop after three repairs rather than looping.
Windows MBPP evaluator	The upstream POSIX evaluator cannot execute directly on Windows.	Use a networkless, read-only Docker Python runner with resource limits; this is an evaluation adapter, not a model-quality change.

These are intentionally small, reproducible local samples. They do not replace official full-benchmark scores, and repaired-output results must never be reported as raw one-pass scores.

Always-on personality and final-output message

The installer writes Q36-Always-On-System-Profile.txt locally and embeds the same content into the Ollama Modelfile. It is sent for every command by the supplied llama.cpp client wrapper. Personality controls tone; strict compiler checks become decisive when a request has exact output constraints, so ordinary conversation remains natural.

Reproducing the benchmark-only track

The reproducible Q4_K_M track uses 9,600 context tokens. It is explicitly benchmark-only and does not replace the normal context chosen for a deployment. Its task-specific settings are:

GSM8K fixed sample: thinking on, max_tokens=1024.
BBH Boolean Expressions with the double-newline CoT stop: thinking off, max_tokens=1024.
Agentic code repair: thinking off, visible tests, at most three repair attempts.

The commands and limitations are in BENCHMARK-PLAN.md.