Instructions to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed 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 conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed
# Run inference directly in the terminal:
llama cli -hf conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed
# Run inference directly in the terminal:
llama cli -hf conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

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 conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed
# Run inference directly in the terminal:
./llama-cli -hf conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

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 conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed
# Run inference directly in the terminal:
./build/bin/llama-cli -hf conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

Use Docker

docker model run hf.co/conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

LM Studio
Jan

vLLM

How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

Ollama
How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with Ollama:
```
ollama run hf.co/conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed
```

Unsloth Studio

How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed to start chatting

How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

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": "conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with Docker Model Runner:
```
docker model run hf.co/conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed
```

Lemonade

How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

Run and chat with the model

lemonade run user.ornith15-35b-a3b-apex-mtp-fixed-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

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 conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

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 "conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed" \
  --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"

Ornith-1.5-35B-A3B — APEX-MTP-Fixed

Repaired multi-token-prediction (MTP) head build of Ornith-1.5-35B-A3B, exported as GGUF.

The stock Ornith-1.5 MTP head shipped untrained — its RMSNorm scales read garbage (~1e31 / NaN) — so speculative decoding was dead on arrival. This build splices in the Avifenesh continued-trained MTP head (dequantized NVFP4 → f32 → Q8_0), restoring a properly-trained head so in-model MTP speculative decoding actually works.

Verified model facts (read from this exact GGUF)

Property	Value
Architecture	`qwen35moe`
Parameters	35.505B total (256 experts, 8 active, ~2.6B active per token)
Context length	262,144 (256k)
Decoder blocks	41
MTP	`nextn_predict_layers = 1` (MTP spec-decode enabled)
Embedding dim	2048, RoPE base 1e7, full-attention every 4th layer, SSM layers

Quantization (verified from the blob)

Component	GGML type	Count
Routed experts	Q4_K	221
Higher-precision layers	Q6_K	121
Deepest-compressed experts	Q3_K	90
MTP head (`blk.40`)	Q8_0	11
MTP head norms	F32	9
Norms / embeddings	F32	310
File size	17.44 GB (17,437,861,152 B)

The MTP head fix

Original head: untrained — RMSNorm scales read garbage (~1e31, NaN), so spec-decode output was nonsense.
Avifenesh continued-trained head: RMSNorm scales 0.97–1.05 (a properly trained head).
Effect: fixes depth-2/3 prediction collapse (0.80/0.27/0.13 → 0.81/0.58/0.43) and lifts draft acceptance ≈ 0.352 → 0.431.
Splice integrity: NVFP4 → f32 → Q8_0 round-trip, MSE 0.000000 (lossless).

Usage

Runs on llama.cpp and Ollama (both honor qwen35moe MTP via nextn_predict_layers=1). Fast on a 4070-class GPU.

# Ollama (also published there)
ollama run slickwillies/ornith15-35b-a3b-apex-mtp-fixed

Acknowledgements

Base: ornith-ai/Ornith-1.5-35B-A3B
Trained MTP head: Avifenesh continued-training
GGUF base: mudler/Ornith-1.5-35B-A3B-APEX-MTP-GGUF (APEX-MTP-Compact)
Splice + repack: configur8tor

Downloads last month: 342

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed

Base model

ornith-ai/Ornith-1.5-35B-A3B

Quantized

(85)

this model