Instructions to use protoLabsAI/Ornith-1.0-35B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use protoLabsAI/Ornith-1.0-35B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="protoLabsAI/Ornith-1.0-35B-FP8")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("protoLabsAI/Ornith-1.0-35B-FP8")
model = AutoModelForMultimodalLM.from_pretrained("protoLabsAI/Ornith-1.0-35B-FP8")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use protoLabsAI/Ornith-1.0-35B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "protoLabsAI/Ornith-1.0-35B-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "protoLabsAI/Ornith-1.0-35B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/protoLabsAI/Ornith-1.0-35B-FP8

SGLang

How to use protoLabsAI/Ornith-1.0-35B-FP8 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 "protoLabsAI/Ornith-1.0-35B-FP8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "protoLabsAI/Ornith-1.0-35B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "protoLabsAI/Ornith-1.0-35B-FP8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "protoLabsAI/Ornith-1.0-35B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use protoLabsAI/Ornith-1.0-35B-FP8 with Docker Model Runner:
```
docker model run hf.co/protoLabsAI/Ornith-1.0-35B-FP8
```

Ornith-1.0-35B-FP8

Block-wise FP8 (E4M3) quantization of deepreinforce-ai/Ornith-1.0-35B — DeepReinforce's self-scaffolding agentic-coding MoE (Qwen3.5-35B-A3B hybrid). Served size ~35 GB; fits a single 80–96 GB GPU with full context.

Quantized and serve-validated by protoLabs on RTX PRO 6000 Blackwell (vLLM 0.22.1).

Why this exists

The upstream FP8 release was reported broken. This is a clean, serve-validated FP8 built to the Qwen official block-wise format (served natively on vLLM's fused-MoE Triton path), with the entire linear-attention / SSM path and the MoE router kept in bf16 — FP8-quantizing those corrupts the hybrid SSM and is the most likely failure mode for a naive FP8 of this architecture.

Quantization recipe

Scheme: block-wise [128, 128] FP8 E4M3, dynamic per-token activations (quant_method: fp8, activation_scheme: dynamic).
Quantized: all expert FFNs (gate/up/down), shared-expert FFNs, full-attention projections (q/k/v/o).
Kept bf16 (modules_to_not_convert): lm_head, embed_tokens, MoE router gates (mlp.gate, shared_expert_gate), all linear_attn.* (SSM: in_proj_*, out_proj, conv1d, A_log, dt_bias), all norms, and the vision tower.
Streaming tensor-by-tensor quantizer (peak RAM ≈ 2× largest tensor) — no full-model load.

Validation (protoLabs harness, thinking-on, single trial)

Smoke: coherent across coding / reasoning / long-form / multilingual / tool-calling — no gibberish, no reasoning leak.

Metric	bf16 source	This FP8
custom coding (one-shot)	1.00 (10/10)	0.975 (9/10)
function-call	93% (50/54)	89% (48/54)
decode tok/s (1× RTX PRO 6000)	208	207

Deltas are within single-trial run-to-run variance (temp 0.6–0.7); throughput is identical to the source.

Serving (vLLM)

vllm serve protoLabsAI/Ornith-1.0-35B-FP8 \
  --served-model-name ornith-35b \
  --max-model-len 262144 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice --tool-call-parser qwen3_xml \
  --gpu-memory-utilization 0.90 \
  --trust-remote-code

Context: full 256K (262144). Vision: the base is multimodal (Qwen-VL-style image + video tokens) and the vision tower is preserved in bf16 — the recipe above keeps it enabled. For text-only serving (smaller footprint), add --language-model-only. Verified serving with vision on at 256K on RTX PRO 6000 (Blackwell, sm120).

Ornith is a reasoning model: the assistant turn opens with a <think>…</think> block surfaced as reasoning_content; tool calls are emitted as standard tool_calls. Recommended sampling: temperature=0.6, top_p=0.95, top_k=20.

License & attribution

MIT, inheriting Ornith-1.0. All credit for the base model to the DeepReinforce team (blog); this repo only adds the FP8 quantization.

@misc{ornith-35b, title={{Ornith-1.0-35B}: Agentic Coding, Open to All},
  url={https://deep-reinforce.com/ornith_1_0.html}, author={{DeepReinforce Team}}, year={2026}}

Downloads last month: 1,672

Safetensors

Model size

35B params

Tensor type

BF16

F8_E4M3

Model tree for protoLabsAI/Ornith-1.0-35B-FP8

Base model

deepreinforce-ai/Ornith-1.0-35B

Quantized

(82)

this model