Instructions to use julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use julianmb/Ornith-1.5-35B-A3B-ROCmFP4-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 julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf julianmb/Ornith-1.5-35B-A3B-ROCmFP4-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 julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf julianmb/Ornith-1.5-35B-A3B-ROCmFP4-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 julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16

Use Docker

docker model run hf.co/julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16

LM Studio
Jan
Ollama
How to use julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF with Ollama:
```
ollama run hf.co/julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16
```
Unsloth Desktop

How to use julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF: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": "julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16
```

Lemonade

How to use julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16

Run and chat with the model

lemonade run user.Ornith-1.5-35B-A3B-ROCmFP4-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use julianmb/Ornith-1.5-35B-A3B-ROCmFP4-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 julianmb/Ornith-1.5-35B-A3B-ROCmFP4-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 julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf julianmb/Ornith-1.5-35B-A3B-ROCmFP4-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 "julianmb/Ornith-1.5-35B-A3B-ROCmFP4-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"

Ornith-1.5-35B-A3B ROCmFP4

ROCmFP4 quantization of Ornith 1.5 35B-A3B for AMD Strix Halo (gfx1151) and RDNA 3.5 GPUs, produced with the Q4_0_ROCMFP4_STRIX_LEAN preset (FP16 embedding/norm preservation, nextn MTP head kept at q8_0).

Revision 2026-08-28: rebuilt from the ornith-ai aug-24 MTP refresh. the retrained MTP head now verifies at 87.98% draft acceptance (mean 3.70/4 positions) for 105.6 tok/s effective decode on strix halo — speculative decoding is now recommended. note: the new MTP head requires this base revision; do not graft it onto older quants.

Quantization Details

Property	Value
Quant format	`Q4_0_ROCMFP4_STRIX_LEAN` (ROCmFP4)
Bits per weight	4.29
File size	18.16 GiB
SHA256	`0f907917a1bfe4e0ca0d281e5709dcf34b6277063e94fab29491bb5c80fda696`
Vision projector	`mmproj-Ornith-1.5-35B-BF16.gguf` (0.84 GiB)
Projector SHA256	`d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837`
Max Context	262,144 tokens (256K)
Source	Ornith-1.5-35B-A3B-GGUF Q8_0 aug-24 MTP refresh (allow-requantize)
Notes	MTP head tensors preserved at q8_0

Measured Performance (AMD Ryzen AI Max+ 395, Radeon 8060S, Mesa RADV Wave64)

Configuration	Decode
ROCmFP4 bare decode	76.9 tok/s
Q4_K_M baseline	71.5–71.7 tok/s
ROCmFP4 MTP (n4 p0.6, aug-24 refresh)	105.6 tok/s (87.98% draft acceptance, mean 3.70/4)

ROCmFP4 is ~7.5% faster and 16.7% smaller than stock Q4_K_M; with MTP speculative decoding it reaches ~137% of bare decode.

Serving

HaloFPX (Text + Vision)

halofpx pull downloads and verifies both the ROCmFP4 weights and BF16 vision projector:

halofpx pull ornith-1.5-35b
halofpx serve
halofpx load ornith-1.5-35b

halofpx list reports model-weight and vision-projector readiness separately.

Direct llama-server Vision

llama-server \
  -m Ornith-1.5-35B-A3B-ROCmFP4.gguf \
  -mm mmproj-Ornith-1.5-35B-BF16.gguf \
  -ngl 99 -c 131072 -fa on --no-mmap

Full 256K Max Context (Strix Halo 128GB UMA):

llama-server \
  -m Ornith-1.5-35B-A3B-ROCmFP4.gguf \
  -ngl 99 -c 262144 -fa on --no-mmap

Multi-Slot / Conservative Memory (131K Context):

llama-server \
  -m Ornith-1.5-35B-A3B-ROCmFP4.gguf \
  -ngl 99 -c 131072 -fa on --no-mmap

Note: speculative decoding (MTP, --spec-type draft-mtp) is recommended on this model with the aug-24 refresh: measured 87.98% draft acceptance (mean 3.70/4 positions) for 105.6 tok/s effective decode vs 76.9 bare. suggested profile: --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.6 -fa on.

Downloads last month: 3,317

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for julianmb/Ornith-1.5-35B-A3B-ROCmFP4-GGUF

Base model

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

Quantized

(1)

this model