---
base_model: deepreinforce-ai/Ornith-1.0-35B
license: mit
tags:
  - autoround
  - quantized
  - int4
  - coding
  - agentic
  - reasoning
  - multimodal
  - tool-calling
  - qwen3_5_moe
pipeline_tag: text-generation
language:
  - en
---

# Ornith-1.0-35B — INT4 AutoRound

INT4 quantization of [deepreinforce-ai/Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) using [spark-auto-round](https://github.com/whpthomas/spark-auto-round).

## Model Details

| Property | Value |
|---|---|
| Base model | deepreinforce-ai/Ornith-1.0-35B |
| Architecture | Qwen3.5 MoE (256 experts, 8 active) |
| Parameters | 35B |
| Context window | 196,608 tokens |
| Quantization | INT4, group_size=128, symmetric |
| Packing format | auto_round:auto_gptq |
| AutoRound version | 0.14.3 |
| Calibration | 512 samples, 1000 iters |

Shared expert gate layers are kept in FP16 for accuracy.

## Capabilities

- **Agentic coding** — tool-calling with `qwen3_xml` format (OpenAI-compatible)
- **Reasoning** — built-in chain-of-thought via `<think>...</think>` blocks
- **Multimodal** — image + text inputs
- **Long context** — up to 196K tokens

## Benchmarks (base model, BF16)

| Benchmark | Score |
|---|---|
| SWE-bench Verified | 75.6% |
| SWE-bench Pro | 50.4% |
| Terminal-Bench 2.1 | 64.2% |
| NL2Repo | 34.6% |
| Claw-eval Average | 69.8% |

## Usage

### vLLM

```bash
vllm serve cyburn/Ornith-1.0-35B-int4-AutoRound \
  --served-model-name qwen/qwen3.5 \
  --load-format instanttensor \
  --tensor-parallel-size 1 \
  --gpu-memory-utilization 0.80 \
  --kv-cache-dtype fp8 \
  --max-model-len 196608 \
  --max-num-batched-tokens 16384 \
  --attention-backend FLASHINFER \
  --quantization compressed-tensors \
  --enable-prefix-caching \
  --enable-chunked-prefill \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_xml \
  --reasoning-parser qwen3 \
  --chat-template chat_template.jinja \
  --generation-config auto \
  --trust-remote-code
```

Requires vLLM ≥ 0.19.1.

### Transformers

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "cyburn/Ornith-1.0-35B-int4-AutoRound",
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("cyburn/Ornith-1.0-35B-int4-AutoRound")
```

Requires transformers ≥ 5.8.1.

## Quantization

Produced with [spark-auto-round](https://github.com/whpthomas/spark-auto-round) v0.14.3:

```
bits=4, group_size=128, sym=True, iters=1000, nsamples=512
packing_format=auto_round:auto_gptq
```

## License

MIT — same as the base model.