Instructions to use Harsha001/Ornith-1.5-122B-ROCmFPX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Harsha001/Ornith-1.5-122B-ROCmFPX 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 Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED
# Run inference directly in the terminal:
llama cli -hf Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED
# Run inference directly in the terminal:
llama cli -hf Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

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 Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED
# Run inference directly in the terminal:
./llama-cli -hf Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

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 Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

Use Docker

docker model run hf.co/Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

LM Studio
Jan

vLLM

How to use Harsha001/Ornith-1.5-122B-ROCmFPX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harsha001/Ornith-1.5-122B-ROCmFPX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harsha001/Ornith-1.5-122B-ROCmFPX",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

Ollama

How to use Harsha001/Ornith-1.5-122B-ROCmFPX with Ollama:

ollama run hf.co/Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

Unsloth Desktop

How to use Harsha001/Ornith-1.5-122B-ROCmFPX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

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": "Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Harsha001/Ornith-1.5-122B-ROCmFPX with Docker Model Runner:
```
docker model run hf.co/Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED
```

Lemonade

How to use Harsha001/Ornith-1.5-122B-ROCmFPX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

Run and chat with the model

lemonade run user.Ornith-1.5-122B-ROCmFPX-Q4_0_BALANCED

List all available models

lemonade list

Hermes Agent

How to use Harsha001/Ornith-1.5-122B-ROCmFPX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

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 Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Harsha001/Ornith-1.5-122B-ROCmFPX with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED

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 "Harsha001/Ornith-1.5-122B-ROCmFPX:Q4_0_BALANCED" \
  --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-1.5-122B — ROCmFPX Q4 GGUF

ornith-ai/Ornith-1.5-122B quantized to two 4-bit ROCmFPX types. ROCmFPX is a llama.cpp fork with AMD-oriented low-bit weight types for Vulkan and HIP/ROCm.

Q4_0_ROCMFP4, balanced: the closest 4-bit file to the original. Start here.
Q4_0_ROCMFP4_STRIX: the recipe ROCmFPX tuned for speed on AMD Strix Halo (Ryzen AI Max, gfx1151); smaller, a bit less exact.

Download one variant, not the whole repo. The repo holds both versions (146 GB together); you need only one: balanced is 80 GB, Strix is 65 GB, plus 0.9 GB for image input. Each is split into parts below 50 GB; point llama.cpp at the first part and it loads the rest. Image input works with the included F16 vision projector (--mmproj).

# balanced (80 GB)
hf download Harsha001/Ornith-1.5-122B-ROCmFPX --include "*Q4_0_BALANCED-*" "mmproj*" --local-dir Ornith-1.5-122B
# or Strix (65 GB)
hf download Harsha001/Ornith-1.5-122B-ROCmFPX --include "*Q4_0_STRIX-*" "mmproj*" --local-dir Ornith-1.5-122B

Memory on a 128 GB Strix Halo: the GPU can only use the share of memory given to it. Give it 96 GB (in the BIOS on Windows, or through the GTT/TTM limit on Linux): then either variant fits with room for context. With a 64/64 split neither fits with usable context (Strix would leave about 3 GB).

These files only load in the ROCmFPX fork. Stock llama.cpp, LM Studio and Ollama do not know these types.

Files

File	Size	Variant
`Ornith-1.5-122B-ROCmFP4-Q4_0_BALANCED-00001-of-00002.gguf`	44.7 GB	balanced
`Ornith-1.5-122B-ROCmFP4-Q4_0_BALANCED-00002-of-00002.gguf`	35.3 GB	balanced
`Ornith-1.5-122B-ROCmFP4-Q4_0_STRIX-00001-of-00002.gguf`	44.8 GB	Strix
`Ornith-1.5-122B-ROCmFP4-Q4_0_STRIX-00002-of-00002.gguf`	20.5 GB	Strix
`mmproj-Ornith-1.5-122B-f16.gguf`	0.9 GB	image input, for both

The files are named ROCmFP4-Q4_0_BALANCED and ROCmFP4-Q4_0_STRIX so that Hugging Face's size panel counts the two versions separately; it reads both full type names as the same label. The weights inside are Q4_0_ROCMFP4 and the Q4_0_ROCMFP4_STRIX recipe, unchanged.

Measured quality

Measured against the BF16 model (228 GB) on WikiText-2 test, 12 chunks of 512 tokens, CPU backend. KLD is the mean KL divergence of the token distribution from BF16 (lower is better). Same top is how often the quant picks the same next token as BF16.

Model	PPL	KLD	Same top
BF16 (original)	4.8585	0	100%
`Q4_0_ROCMFP4` (balanced, 80 GB)	5.2165	0.1769	84.41%
`Q4_0_ROCMFP4_STRIX` (Strix, 65 GB)	5.3642	0.2406	81.57%
`Q4_K_M` (yardstick only, not published here, 70 GB)	5.1149	0.1564	84.58%

This model is more sensitive to 4-bit quantization than most: even the standard Q4_K_M, made from the same BF16 weights and importance matrix, moves clearly away from BF16. Twelve chunks is a small sample, so take the numbers as a guide (± about 0.01 on KLD).

How this was made

convert_hf_to_gguf.py --no-mtp --outtype bf16 from the ROCmFPX fork (fb08d7c). The multi-token-prediction head is left out, because the fork does not use it for decoding.
Importance matrix: bartowski's Ornith-1.5-122B-imatrix.gguf (573 chunks × 512 tokens of his calibration set v6). Computing our own from the 228 GB BF16 model on a CPU with 121 GB of RAM would take about 12 hours. Thanks to bartowski.
llama-quantize --imatrix from ROCmFPX (fb08d7c), from the BF16 weights, one run per type.
Perplexity and KL divergence on the CPU backend. The fork's CUDA kernels for these types are not correct on NVIDIA, so no GPU numbers are used.
Each file was checked with a short chat prompt and an image prompt before upload.

Run

git clone https://github.com/charlie12345/ROCmFPX && cd ROCmFPX
cmake -B build -DGGML_VULKAN=ON          # or -DGGML_HIP=ON -DAMDGPU_TARGETS=gfx1151
cmake --build build --target llama-server -j
build/bin/llama-server -m Ornith-1.5-122B-ROCmFP4-Q4_0_BALANCED-00001-of-00002.gguf --mmproj mmproj-Ornith-1.5-122B-f16.gguf -ngl 999 -fa on --jinja

License

MIT, same as the base model. All credit for the model goes to Ornith AI.

Downloads last month: 44

GGUF

Model size

122B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for Harsha001/Ornith-1.5-122B-ROCmFPX

Base model

ornith-ai/Ornith-1.5-122B

Quantized

(35)

this model