Instructions to use SC117/Ornith-1.0-35B-MTP-APEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SC117/Ornith-1.0-35B-MTP-APEX-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SC117/Ornith-1.0-35B-MTP-APEX-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SC117/Ornith-1.0-35B-MTP-APEX-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SC117/Ornith-1.0-35B-MTP-APEX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SC117/Ornith-1.0-35B-MTP-APEX-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SC117/Ornith-1.0-35B-MTP-APEX-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SC117/Ornith-1.0-35B-MTP-APEX-GGUF

SGLang

How to use SC117/Ornith-1.0-35B-MTP-APEX-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SC117/Ornith-1.0-35B-MTP-APEX-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SC117/Ornith-1.0-35B-MTP-APEX-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SC117/Ornith-1.0-35B-MTP-APEX-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SC117/Ornith-1.0-35B-MTP-APEX-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SC117/Ornith-1.0-35B-MTP-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/SC117/Ornith-1.0-35B-MTP-APEX-GGUF
```

Works like a charm

by blackfan23 - opened Jul 2

Discussion

blackfan23

Jul 2

Thank you for your contribution.

SC117

Owner Jul 3

Thank you for your contribution.

Thanks for trying it out! Glad it's working well for you 🐦

SolsticeAI

Jul 8

•

edited Jul 8

i wanted to ask a question, how do these models perform like in the real world will i compact or mini work out i have insufficient ram for the larger ones

blackfan23

Jul 8

I have testet both, have a macbook with 32GB unified ram. mini works very well on real world tasks. The difference up to quality is marginal in my experience

SolsticeAI

Jul 8

how about like vs the original ornith 35b or claude opus 4.6

blackfan23

Jul 8

I have only been using APEX quants even earlier, but Qwen 36 APEX has outperformed Qwen 36 normal for me. I have not done that comparison for ornith. Claude opus 4.6 (via antigravity) is still better, but that is to be expected.

SolsticeAI

Jul 8

please PLEASE be more specific which quant of which

blackfan23

Jul 8

Qwen 4KM
Qwen Apex Balanced and Quality (I matrix)
Opus, don't know

SolsticeAI

Jul 8

oh ok then tysm

VitreousCut

Jul 10

Loops real bad for me.

SolsticeAI

Jul 10

oh ok

Andy-P

17 days ago

I've settled on this model now, it works really well on my split 3060/4070 24gb system.
With the ornith-1.0-35b-mtp-apex I Mini version, 128000 context and Q4_0 kv cache, I get 1120/52 tok/s parse/generate.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment