# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText
processor = AutoProcessor.from_pretrained("GestaltLabs/Ornstein-3.6-27B")
model = AutoModelForImageTextToText.from_pretrained("GestaltLabs/Ornstein-3.6-27B")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
{"type": "text", "text": "What animal is on the candy?"}
]
},
]
inputs = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))
Ornstein-3.6-27B
A fine-tune of Qwen 3.6 27B, the dense multimodal (vision + text) member of the Qwen 3.6 family with hybrid linear + full attention. Part of the Ornstein series — reasoning- and agent-oriented fine-tunes built on a custom data curation pipeline.
GGUF quantizations available at GestaltLabs/Ornstein-3.6-27B-GGUF — Q8_0 down through aggressive 3-bit I-quants.
Support This Work
I'm a PhD student in visual neuroscience at the University of Toronto who also happens to spend way too much time fine-tuning, merging, and quantizing open-weight models on rented H100s and a local DGX Spark. All training compute is self-funded — balancing GPU costs against a student budget. If my uploads have been useful to you, consider buying a PhD student a coffee. It goes a long way toward keeping these experiments running.
Details
- Developed by: GestaltLabs
- Architecture:
Qwen3_5ForConditionalGeneration— Qwen 3.6 dense with linear + full attention interleaved (Gated Delta Net) + vision encoder - Parameters: ~27B total (dense, multimodal)
- Hidden size / layers: 5120 / 64
- Attention: 24 heads, 4 KV heads, head_dim 256, full-attention every 4 layers (linear otherwise)
- Context length: 262,144 tokens
- License: Apache 2.0
- Base model: unsloth/Qwen3.6-27B
- Training framework: Unsloth
Usage
Transformers
from transformers import AutoModelForImageTextToText, AutoProcessor
model_id = "GestaltLabs/Ornstein-3.6-27B"
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True
)
messages = [{"role": "user", "content": [{"type": "text", "text": "Write a haiku about hybrid attention."}]}]
inputs = processor.apply_chat_template(
messages, add_generation_prompt=True, tokenize=True, return_tensors="pt"
).to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(processor.batch_decode(out[:, inputs["input_ids"].shape[-1]:], skip_special_tokens=True)[0])
llama.cpp (via GGUF)
See the GGUF repo — pick a quant that fits your memory (Q4_K_M is a strong default for 24 GB cards).
License
Apache 2.0 — inherited from the Qwen 3.6 base release.
- Downloads last month
- 253
Model tree for GestaltLabs/Ornstein-3.6-27B
Base model
Qwen/Qwen3.6-27B
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="GestaltLabs/Ornstein-3.6-27B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)