Instructions to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN 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 pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16
# Run inference directly in the terminal:
llama cli -hf pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16
# Run inference directly in the terminal:
llama cli -hf pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN: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 pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16
# Run inference directly in the terminal:
./llama-cli -hf pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN: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 pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16

Use Docker

docker model run hf.co/pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16

LM Studio
Jan

vLLM

How to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN",
		"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/pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16

Ollama
How to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN with Ollama:
```
ollama run hf.co/pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16
```
Unsloth Desktop

How to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16

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": "pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN with Docker Model Runner:
```
docker model run hf.co/pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16
```

Lemonade

How to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16

Run and chat with the model

lemonade run user.Ornith-1.5-35B-ROCmFP4-STRIX_LEAN-BF16

List all available models

lemonade list

Hermes Agent

How to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN: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 pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN: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 "pugant/Ornith-1.5-35B-ROCmFP4-STRIX_LEAN: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"

pugant commited on 14 days ago

Commit

4494a5c

verified ·

1 Parent(s): ab96217

docs: point lab references to strix-nebulosa (repo rename)

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ quantized_by: pugant
 ## TL;DR
-`Ornith-1.5-35B` (35B params, 3B active per token, Qwen3.5-VL-MoE family) quantized to **`Q4_0_ROCMFP4_STRIX_LEAN`** (type 106 preset, ~4.29 BPW). Tuned for **AMD Strix Halo (gfx1151 / RDNA 3.5)** on the **ROCmFPX fork family** — we serve and benchmark these files on **our lab runtime** (full source: [pugant/strix-halo-llamacpp-lab](https://github.com/pugant/strix-halo-llamacpp-lab/tree/main/rocmfpx); upstream: [charlie12345/ROCmFPX](https://github.com/charlie12345/ROCmFPX)). Runs the full vision + text multimodal model in ~17.7 GiB.
 ## ⚠️ Critical warnings — read before downloading
@@ -176,10 +176,10 @@ No affiliation with AMD, Qwen, DeepReinforce, bartowski, unsloth, kyuz0, or char
 ---
 ## Runtime
-**Benchmark environment:** one bare-metal AMD Strix Halo (Ryzen AI MAX+ 395, 128 GB) — full dated configuration and measurement policy: [BARE-METAL.md](https://github.com/pugant/strix-halo-llamacpp-lab/blob/main/BARE-METAL.md)
 Requires a ROCmFPX fork build (custom tensor types — stock llama.cpp refuses the file).
-**Recommended: our lab build** ([pugant/strix-halo-llamacpp-lab](https://github.com/pugant/strix-halo-llamacpp-lab), `main`) —
 reasoning budget and persistent prompt cache on every model; drafter features
 where the model ships one: see the engine section of its README.

 ## TL;DR
+`Ornith-1.5-35B` (35B params, 3B active per token, Qwen3.5-VL-MoE family) quantized to **`Q4_0_ROCMFP4_STRIX_LEAN`** (type 106 preset, ~4.29 BPW). Tuned for **AMD Strix Halo (gfx1151 / RDNA 3.5)** on the **ROCmFPX fork family** — we serve and benchmark these files on **our lab runtime** (full source: [pugant/strix-nebulosa](https://github.com/pugant/strix-nebulosa/tree/main/rocmfpx); upstream: [charlie12345/ROCmFPX](https://github.com/charlie12345/ROCmFPX)). Runs the full vision + text multimodal model in ~17.7 GiB.
 ## ⚠️ Critical warnings — read before downloading
 ---
 ## Runtime
+**Benchmark environment:** one bare-metal AMD Strix Halo (Ryzen AI MAX+ 395, 128 GB) — full dated configuration and measurement policy: [BARE-METAL.md](https://github.com/pugant/strix-nebulosa/blob/main/BARE-METAL.md)
 Requires a ROCmFPX fork build (custom tensor types — stock llama.cpp refuses the file).
+**Recommended: our lab build** ([pugant/strix-nebulosa](https://github.com/pugant/strix-nebulosa), `main`) —
 reasoning budget and persistent prompt cache on every model; drafter features
 where the model ships one: see the engine section of its README.