Instructions to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S 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 YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16
# Run inference directly in the terminal:
llama cli -hf YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16
# Run inference directly in the terminal:
llama cli -hf YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

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 YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16
# Run inference directly in the terminal:
./llama-cli -hf YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

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 YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

Use Docker

docker model run hf.co/YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

LM Studio
Jan

vLLM

How to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YTan2000/Ornith-1.5-35B-A3B-TQ3_4S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YTan2000/Ornith-1.5-35B-A3B-TQ3_4S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

Ollama
How to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S with Ollama:
```
ollama run hf.co/YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16
```
Unsloth Desktop

How to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

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": "YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S with Docker Model Runner:
```
docker model run hf.co/YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16
```

Lemonade

How to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

Run and chat with the model

lemonade run user.Ornith-1.5-35B-A3B-TQ3_4S-F16

List all available models

lemonade list

Hermes Agent

How to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

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 YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use YTan2000/Ornith-1.5-35B-A3B-TQ3_4S with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16

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 "YTan2000/Ornith-1.5-35B-A3B-TQ3_4S:F16" \
  --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-TQ3_4S / README.md

YTan2000

Upload README.md with huggingface_hub

fcd66dc verified 12 days ago

preview code

Raw

History Blame Contribute Delete

5.87 kB

metadata

license: mit
language:
  - en
library_name: gguf
pipeline_tag: text-generation
model_name: Ornith-1.5-35B-A3B-TQ3_4S
tags:
  - gguf
  - llama.cpp
  - qwen
  - qwen3.5
  - qwen3.5-moe
  - multimodal
  - vision
  - ornith
  - turboquant
  - tq3_4s
base_model:
  - ornith-ai/Ornith-1.5-35B-A3B
model-index:
  - name: Ornith-1.5-35B-A3B-TQ3_4S
    results: []

Ornith-1.5-35B-A3B-TQ3_4S

Ornith-1.5-35B-A3B-TQ3_4S is a compact TurboQuant GGUF build of ornith-ai/Ornith-1.5-35B-A3B.

Required Runtime

This model uses the custom TQ3_4S tensor type and requires turbo-tan/llama.cpp-tq3.

Stock llama.cpp builds without TurboQuant support cannot load this model.

This is the standard 35B-A3B MoE model, not an MTP release. Do not add draft-MTP speculative-decoding flags.

Ornith-1.5-35B-A3B is a Qwen3.5-based multimodal model. Vision is optional — load the mmproj projector to enable image input (see Vision (Multimodal)).

Files

Ornith-1.5-35B-A3B-TQ3_4S.gguf - main model, 17.00 GiB
thumbnail.png - model card banner

Architecture

Property	Value
Architecture	Qwen3.5-MoE (qwen35moe)
Total parameters	35.9B
Active parameters	~3B per token
Expert count	256
Active experts	8
Block count	41
Attention interval	Every 4th layer (full attention)
SSM layers	DeltaNet (3/4 of layers)
Context length	262,144 (source)
Quantization	TQ3_4S (4.06 BPW)

Build the Required Runtime

git clone https://github.com/turbo-tan/llama.cpp-tq3
cd llama.cpp-tq3

cmake -S . -B build \
  -DCMAKE_BUILD_TYPE=Release \
  -DGGML_CUDA=ON \
  -DGGML_CUDA_FA_ALL_QUANTS=OFF \
  -DGGML_CUDA_GRAPHS=ON

cmake --build build --target llama-server -j

For an RTX 3090, -DCMAKE_CUDA_ARCHITECTURES=86 may be added explicitly. Use the architecture matching your GPU on other systems.

Recommended Runtime

Validated on an NVIDIA GeForce RTX 3090 Founders Edition with 24 GiB VRAM:

./build/bin/llama-server \
  -m Ornith-1.5-35B-A3B-TQ3_4S.gguf \
  --alias Ornith-1.5-35B-A3B-TQ3_4S \
  --host 127.0.0.1 --port 8080 \
  -c 32768 -np 1 -ngl 99 -fa on \
  -ctk q8_0 -ctv tq3_0 \
  --reasoning off --jinja

Runtime notes:

-fa on enables flash attention at runtime.
The validated CUDA build uses GGML_CUDA_FA_ALL_QUANTS=OFF.
-ngl 99 fully offloads the model on supported GPUs. Avoid partial offload when comparing the published speed.
Reduce context from 32768 if the available VRAM is lower than 24 GiB.

Quick Smoke Test

curl -s http://127.0.0.1:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"Ornith-1.5-35B-A3B-TQ3_4S","messages":[{"role":"user","content":"Write ONLY the word ok."}],"max_tokens":16,"temperature":0.0}'

Expected assistant content:

ok

Local Measurements

Metric	Result
Generation speed (short ctx)	171.1 tok/s
Size	17.00 GiB
Quantization	TQ3_4S (4.06 BPW)

Measured on RTX 3090 FE with the launch settings above. Generation speed is token throughput excluding prompt processing.

Context-Length Decode Speed

Decode throughput measured with 512-token generation across varying prompt lengths. Compared against Ornith-1.0-35B-TQ3_4S (dense 35B, 13 GiB) on the same hardware and binary.

Context Size	Ornith-1.5 MoE (tok/s)	Ornith-1.0 Dense (tok/s)	Speedup
4K	168.9	156.2	+8.1%
8K	163.4	153.6	+6.4%
16K	147.9	140.1	+5.6%
32K	125.7	118.9	+5.7%
64K	95.5	91.9	+3.9%
128K	89.2	85.5	+4.3%
256K	88.6	84.4	+5.0%

Runtime: turbo-tan/llama.cpp-tq3 commit 47635d703, -ngl 99 -fa on -ctk q8_0 -ctv tq3_0 -c 262144 --reasoning off, NVIDIA RTX 3090 24GB.

The MoE architecture (3B active parameters) delivers a consistent 4–8% decode speedup over the dense 35B variant across all context sizes.

Benchmark Summary

Suite	Score	Pass Rate
Coding	93.8%	11/12 tasks
Tool Calling	91.7%	13/15 tasks
Data Extraction	85.8%	10/15 tasks
Instruction Following	64.5%	5/15 tasks
Hard86 Coding	47.7%	41/86 tests

Notes:

All benchmarks run with --reasoning off for maximum speed
MoE architecture (3B active parameters) enables fast inference
Coding and tool calling scores are competitive with dense 35B models
Instruction following shows room for improvement on complex multi-constraint tasks

Conversion Recipe

# 1. Convert safetensors to F16 GGUF
python convert_hf_to_gguf.py \
  ornith-ai/Ornith-1.5-35B-A3B \
  --outfile Ornith-1.5-35B-A3B-F16.gguf \
  --outtype f16

# 2. Quantize to TQ3_4S
./build/bin/llama-quantize \
  Ornith-1.5-35B-A3B-F16.gguf \
  Ornith-1.5-35B-A3B-TQ3_4S.gguf \
  tq3_4s

Vision (Multimodal)

Ornith-1.5-35B-A3B is a multimodal model. To enable image input, add the vision projector with --mmproj:

./build/bin/llama-server \
  -m Ornith-1.5-35B-A3B-TQ3_4S.gguf \
  --mmproj mmproj-f16.gguf \
  --alias Ornith-1.5-35B-A3B-TQ3_4S \
  --host 127.0.0.1 --port 8080 \
  -c 32768 -np 1 -ngl 99 -fa on \
  -ctk q8_0 -ctv tq3_0 \
  --reasoning off --jinja

Validation Notes

Benchmark results are local measurements, not claims from the parent model repository.

License

Use is subject to the base model license and the licenses of turbo-tan/llama.cpp-tq3.