Instructions to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant 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 TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant
# Run inference directly in the terminal:
llama cli -hf TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant
# Run inference directly in the terminal:
llama cli -hf TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant
# Run inference directly in the terminal:
./build/bin/llama cli -hf TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

Use Docker

docker model run hf.co/TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

Llama new
LM Studio
Jan

vLLM

How to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

Ollama
How to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant with Ollama:
```
ollama run hf.co/TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant
```
Unsloth Desktop

How to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

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": "TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant with Docker Model Runner:
```
docker model run hf.co/TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant
```

Lemonade

How to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

Run and chat with the model

lemonade run user.Ornith-1.5-Reap50-12Gcard_mixQuant-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

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 TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

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 "TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant" \
  --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"

Model Card for Model ID

A fine mix-quantified and REAP-50 version for Ornith-1.5 that is specially designed for 12GB cards.

Model Details

Model Description

**Base model: Ornith-1.5-35B-A3B Ttimms/Ornith-1.5-35B-A3B-REAP-50-bf16
**Quantized by :TSalpha
**License: mit
**Model type: MoE

quantify methods

**layer0-14: IQ2_XXS
**layer15-30: IQ3_XXS
**layer31: IQ3_S
**layer32-39: IQ4_XS
**Shared experts(40layers): IQ4_XS
**attn_qkv / attn_gate、attn_q/k/v/o:Q8_0
**ssm_alpha / ssm_beta / ssm_out:Q8_0
**token_embd / output IQ4_XS
**all norm、ssm_a、ssm_conv1d、ssm_dt.bias、ffn_gate_inp(_shexp)、output_norm F32

Uses

**The model runs well inside a llama.cpp. And maximum context of 256K can be reached with params below on 12G card.
**Suggested params: -c 262144 -ngl 99 -ctk q5_1 -ctv q5_0 -fa on --jinja -np 1 --temp 1 --top-k 20 --top-p 0.95 --min-p 0.10

Evaluation

-*10 chunk ppl comparison with original f16(lower means better performance)

**model-----------------size--------ppl
**f16--------------------- 34.57 GiB 2.3849
**IQ4_XS(this model)7.39 GiB 2.4425
**Q3_K------------------ 9.35 GiB 2.4958
**q2-60pct + imatrix- 8.03 GiB 2.5112
**Q4 swich to MXFP4 7.39 GiB 2.5335
**24IQ2+16IQ4-------- 7.40 GiB 2.5537
the other 5 files are not here.

Hardware

Test runs on RTX5070ti laptop GPU(12G) with 90token/s of max speed. Real agent coding have an output approxly 50t/s tested on Kimicode.

License & Credits

 MIT (inherited from `ornith-ai/Ornith-1.5-35B-A3B`).

 - Base model: [ornith-ai/Ornith-1.5-35B-A3B](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B)
 - Pruned checkpoint:
        [Ttimms/Ornith-1.5-35B-A3B-REAP-50-bf16](https://huggingface.co/Ttimms/Ornith-1.5-35B-A3B-REAP-50-bf16)
   (REAP method: [CerebrasResearch/reap](https://github.com/CerebrasResearch/reap))
 - Quantization & imatrix: TSalpha (local llama.cpp)

Downloads last month: 136

GGUF

Model size

19B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for TSalpha/Ornith-1.5-Reap50-12Gcard_mixQuant

Base model

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

Quantized

(209)

this model