Instructions to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF with Trellis:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-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 Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF
# Run inference directly in the terminal:
llama cli -hf Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF
# Run inference directly in the terminal:
llama cli -hf Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

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 Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

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 Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

Use Docker

docker model run hf.co/Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

LM Studio
Jan
Ollama
How to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF with Ollama:
```
ollama run hf.co/Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF
```
Unsloth Desktop

How to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

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": "Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF with Docker Model Runner:
```
docker model run hf.co/Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF
```

Lemonade

How to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

Run and chat with the model

lemonade run user.Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-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 Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

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 Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

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 "Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF" \
  --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"

REQUIRES ik_llama.cpp or its derivatives

INCOMPATIBLE with mainline llama.cpp and its derivatives (as of August 16th, 2026)

What's that?

A ik_llama.cpp compatible quantization of Gryphe/WorldSim-Opus-3.6-35B-A3B, utilizing:

Q8_0 for SSM tensors
IQ6_K for embeddings, output, shared experts, attention tensors in global self-attn layers
IQ4_KT for sparse experts and attention in local attn layers.

The intention behind such a recipe is squeezing the most sparse experts brainpower in the least amount of space, with absolutely no compromise on long-context attention.

Deliberately stepping away from mixed math/article/story/rp soup datasets, imatrix dataset is a random conversation ~250000-token prune of Squish42/bluemoon-fandom-1-1-rp-cleaned with some turn-based conversation data added from bartowski's calibration data. The imatrix is provided.

For RP-specific finetunes not aimed at being a "general assistant", the weights engaged in creative writing must be preserved first.
At least that's how the theory goes!

Disclosure

WYSIWYG. My only contribution is compute. This is not my merge. Assume WTFPL licensing where no other license implicitly applies. Have fun.

Model card incomplete. Tests and comparisons may be uploaded at a later date.

Downloads last month: 266

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

Gryphe/WorldSim-Opus-3.6-35B-A3B

Quantized

(7)

this model

Koshkasa
/

Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

REQUIRES ik_llama.cpp or its derivatives

INCOMPATIBLE with mainline llama.cpp and its derivatives (as of August 16th, 2026)

What's that?

Disclosure

Model card incomplete. Tests and comparisons may be uploaded at a later date.

Model tree for Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF

Dataset used to train Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-IQ4_KT-GGUF