Instructions to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF",
	filename="Ornith-1.0-35B-NVFP4-noMTP-BF16.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-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 utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

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 utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

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 utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

Use Docker

docker model run hf.co/utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

LM Studio
Jan

vLLM

How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF",
		"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/utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

Ollama
How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF with Ollama:
```
ollama run hf.co/utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16
```

Unsloth Studio

How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF 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 utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF 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 utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF to start chatting

How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-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 utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

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 utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

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 "utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16" \
  --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"

Docker Model Runner
How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF with Docker Model Runner:
```
docker model run hf.co/utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16
```

Lemonade

How to use utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull utautako/Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF:BF16

Run and chat with the model

lemonade run user.Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF-BF16

List all available models

lemonade list

Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF / README.md

utautako

Trim benchmark card back to original concision (numbers only)

b368a51 verified 5 days ago

preview code

Raw

History Blame Contribute Delete

6.43 kB

	---
	license: mit
	pipeline_tag: image-text-to-text
	library_name: llama.cpp
	base_model:
	- sakamakismile/Ornith-1.0-35B-NVFP4
	- deepreinforce-ai/Ornith-1.0-35B
	base_model_relation: quantized
	language:
	- en
	tags:
	- gguf
	- llama-cpp
	- qwen
	- qwen3_5_moe
	- qwen35moe
	- nvfp4
	- compressed-tensors
	- vision
	- vlm
	- multimodal
	- mixture-of-experts
	- agentic-coding
	- quantized
	- rtx-5090
	- blackwell
	---

	# Ornith-1.0-35B-NVFP4-noMTP-BF16-GGUF

	GGUF conversion of [`sakamakismile/Ornith-1.0-35B-NVFP4`](https://huggingface.co/sakamakismile/Ornith-1.0-35B-NVFP4),
	preserving the compressed-tensors NVFP4 weights, with a BF16 vision projector (mmproj) and
	BF16 (lossless) embedding & output layers. Text-only checkpoint (no MTP head). Benchmarked on an RTX 5090 (Blackwell) with `llama-benchy`.

	## Highlights

	- NVFP4 preserved — 430 NVFP4 tensors (MoE experts, attention, linear-attention/SSM) kept in their native 4-bit format, not re-quantized.
	- Lossless embeddings & output — `token_embd` and `lm_head` are kept at BF16 (no Q4_K/Q6_K), so vocabulary and output-projection precision is unchanged from the source.
	- Vision / mmproj — a separate BF16 vision projector enables image-text-to-text.
	- No MTP — the source checkpoint ships no multi-token-prediction head, so this is a clean autoregressive (AR) model (`block_count = 40`).
	- Blackwell native FP4 — prefill/decoding use native FP4 tensor-core kernels on RTX 50-series (`sm_120`).

	## Files

	\| File \| Size \| Description \|
	\|---\|---:\|---\|
	\| `Ornith-1.0-35B-NVFP4-noMTP-BF16.gguf` \| 19.60 GiB \| Main GGUF — NVFP4 body preserved, BF16 `token_embd`/`lm_head` \|
	\| `mmproj-Ornith-1.0-35B-BF16.gguf` \| 861 MiB \| Vision projector (mmproj) for image input \|

	## Usage (llama.cpp)

	```bash
	# Text-only
	llama-server -m Ornith-1.0-35B-NVFP4-noMTP-BF16.gguf --host 0.0.0.0 --port 8080 --jinja

	# With vision (image-text-to-text)
	llama-server -m Ornith-1.0-35B-NVFP4-noMTP-BF16.gguf \
	--mmproj mmproj-Ornith-1.0-35B-BF16.gguf \
	--host 0.0.0.0 --port 8080 --jinja
	```

	For a Blackwell (RTX 50xx) build with native FP4 acceleration, compile llama.cpp with CUDA 12.8+ and
	`-DCMAKE_CUDA_ARCHITECTURES=120`. `-ngl 999` offloads all layers; `-c 262144` uses the full context.

	This is a thinking model. Reasoning is emitted inside `<think>…</think>`. To disable thinking for a
	turn, pass `"chat_template_kwargs": {"enable_thinking": false}` in the request body.

	## Vision

	The model is multimodal (image-text-to-text). Image input requires the separate `mmproj` file via `--mmproj`.
	Verified on llama.cpp with a synthetic image (the model correctly described the shape and color).
	Loading the mmproj has negligible impact on text-generation throughput (see benchmarks).

	## Benchmarks

	RTX 5090 (32 GB), llama.cpp b9812 (`0e53b82a9`, MSVC 19.50, `sm_120a`, `BLACKWELL_NATIVE_FP4=1`),
	`llama-benchy` (pp = 512/4096, tg = 512, runs = 3, `--latency-mode generation`),
	tokenizer `deepreinforce-ai/Ornith-1.0-35B`, ctx = 262144, KV cache `q8_0`. Autoregressive (no spec decoding).

	\| Mode \| pp \| Prefill (pp) tok/s \| Generation (tg) tok/s \| Peak tg \|
	\|---\|---:\|---:\|---:\|---:\|
	\| Text \| 512 \| 6539.84 ± 84.57 \| 193.58 ± 3.20 \| 194.00 \|
	\| Text \| 4096 \| 7754.81 ± 288.02 \| 193.75 ± 1.92 \| 194.33 \|
	\| Vision (+mmproj) \| 512 \| 6076.30 ± 335.59 \| 188.55 ± 1.97 \| 189.00 \|
	\| Vision (+mmproj) \| 4096 \| 7674.93 ± 86.51 \| 190.58 ± 0.24 \| 191.00 \|

	Coherence test PASSED in all runs; generation latency ≈ 112–125 ms.

	## Runtime configuration

	Currently loaded with `llama-server` on RTX 5090:

	\| Parameter \| Value \|
	\|---\|---:\|
	\| Context (`c`) \| 196 608 \|
	\| Max tokens \| 32 768 \|
	\| Speculative decoding \| none \|
	\| Vision projector \| `mmproj-Ornith-1.0-35B-BF16.gguf` \|
	\| KV cache type \| q8_0 \|
	\| VRAM usage \| 22.68 GiB \|

	## Quantization / conversion notes

	Converted with llama.cpp's `convert_hf_to_gguf.py` directly from the `sakamakismile` NVFP4 checkpoint
	(`compressed-tensors`, `format: nvfp4-pack-quantized`), which is auto-detected and re-packed into
	`GGML_TYPE_NVFP4` — no de-quantization to full precision.

	- `--outtype bf16` (not Q4_K). With `bf16`, the NVFP4 body is preserved and the large 2-D weights
	(`token_embd`, `lm_head`) stay at BF16; only small 1-D tensors (norms, biases, router gate, scales)
	are F32. There is no wasteful F32 blow-up of the big weights, so a follow-up `llama-quantize` pass is
	not required to reach a reasonable size (19.60 GiB).
	- `--no-mtp`. The checkpoint's `config.json` declares `mtp_num_hidden_layers: 1` but ships **no MTP
	tensors**; `--no-mtp` keeps `block_count = 40` and avoids requesting an absent MTP head.
	- Tensor make-up: NVFP4 × 430, F32 × 1161 (scales / norms / router gate), BF16 × 2 (`token_embd`, `lm_head`).

	Speed/quality trade-off of BF16 output: keeping `lm_head` at BF16 (~1.0 GiB) costs roughly **14 % of
	generation throughput** versus a fully quantized build (this model ≈ 193 tok/s vs Q4_K_M ≈ 223 tok/s on the
	same hardware), because the output projection over the ~248k-token vocabulary is read every decoding step.
	This build prioritizes lossless embeddings/output; for speed, Q6_K quantization of the output layer via `llama-quantize` is required.

	## Model details

	- Original (quantized) model: [`sakamakismile/Ornith-1.0-35B-NVFP4`](https://huggingface.co/sakamakismile/Ornith-1.0-35B-NVFP4)
	- Base model: [`deepreinforce-ai/Ornith-1.0-35B`](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B)
	- Architecture: `qwen35moe` (Qwen3.5-MoE family; hybrid full + gated-linear attention), `block_count = 40`, no MTP
	- MoE: 256 experts, 8 active; embedding dim 2048; context length 262144
	- Quantization: NVFP4 (430 tensors) preserved; `token_embd`/`lm_head` BF16; scales/norms F32
	- Conversion: `llama.cpp` `convert_hf_to_gguf.py --outtype bf16 --no-mtp` (main) and `--mmproj --outtype bf16` (vision)
	- File sizes: main 19.60 GiB, mmproj 861 MiB

	## License and attribution

	Released under the MIT license, following the upstream models. This is an unofficial GGUF conversion
	of `sakamakismile/Ornith-1.0-35B-NVFP4` (base model `deepreinforce-ai/Ornith-1.0-35B`; NVFP4 quantization by
	`sakamakismile`). It is not affiliated with or endorsed by the original authors. Please consult the original
	model cards for intended use and limitations.