Instructions to use Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead 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 Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4
# Run inference directly in the terminal:
llama cli -hf Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4
# Run inference directly in the terminal:
llama cli -hf Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

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 Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

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 Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

Use Docker

docker model run hf.co/Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

LM Studio
Jan
Ollama
How to use Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead with Ollama:
```
ollama run hf.co/Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4
```
Unsloth Desktop

How to use Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

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": "Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead with Docker Model Runner:
```
docker model run hf.co/Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4
```

Lemonade

How to use Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

Run and chat with the model

lemonade run user.Ornith-1.5-9B-MTP-NVFP4-newhead-NVFP4

List all available models

lemonade list

Hermes Agent

How to use Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

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 Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4

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 "Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead:NVFP4" \
  --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-1.5-9B MTP-NVFP4 — new official head grafted on protoLabs NVFP4 body

Head-graft build: the FP4 body from protoLabsAI/Ornith-1.5-9B-MTP-GGUF (-MTP-NVFP4.gguf, 23 Aug snapshot) with the 15 blk.32 MTP-head tensors replaced by the updated official ones from ornith-ai/Ornith-1.5-9B-GGUF (-Q8_0.gguf, 24 Aug MTP-weights update). Binary splice — tensor names, types (Q8_0/F32) and sizes match byte-identically, so no requantization was needed.

Why

The 24 Aug ornith-ai update improved the MTP head significantly, but no GGUF NVFP4 build carries it yet. This graft gets both: Blackwell-native FP4 kernels (the body) + the new head.

Benchmarks (RTX 5080 16GB, llama.cpp PR #27342 build, 65K ctx)

	old head (protoLabs NVFP4)	this graft
Decode (short)	153 tok/s	183.7 tok/s (+20%)
Decode (long-form)	~140 tok/s	153.8 tok/s
Prefill 12K	6,472 tok/s	8,297 tok/s (+28%)
Acceptance	63%	67%

Quality spot-checks: SimCity one-shot 8/9 (23.6K chars), tool-calling 3/3 with parallel calls.

Usage

llama-server --model Ornith-1.5-9B-MTP-NVFP4-newhead.gguf \
  --n-gpu-layers 99 -fit off --ctx-size 65536 --flash-attn on --jinja \
  --temp 1.0 --top-k 20 --top-p 0.95 --min-p 0.0 --presence-penalty 1.5 \
  --reasoning-budget 4096 \
  --spec-type draft-mtp --spec-draft-n-max 3

Notes:

-fit off + explicit -ngl are mandatory — MTP inverts if any layer lands on CPU
--spec-draft-n-max 3 maximizes throughput (2 = acceptance, 4 regresses)
--reasoning-budget recommended, the xhigh think block otherwise eats the whole max_tokens
Vision: pair with the official mmproj-Ornith-1.5-9B-BF16.gguf from ornith-ai
Requires a recent llama.cpp build with NVFP4 GGUF support (Blackwell GPUs)

Graft recipe

# for each of the 15 blk.32.* tensors (same names/types/sizes in both files):
#   copy bytes at data_offset/n_bytes from official Q8 into a copy of the NVFP4

Credits & license

Body: protoLabsAI (MIT) — NVFP4 GGUF packaging
Head: ornith-ai (MIT) — official MTP weights, 24 Aug update
Model: ornith-ai/Ornith-1.5-9B (MIT)

Downloads last month: 183

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for Cobra91310/Ornith-1.5-9B-MTP-NVFP4-newhead

Base model

ornith-ai/Ornith-1.5-9B

Quantized

(63)

this model