What license applies to offmonreal/Ornith-1.0-35B-MaxQuality-iMatrix-GGUF?

License: mit. Verify terms on Hugging Face before commercial use.

Model Intelligence Sheet

offmonreal/Ornith-1.0-35B-MaxQuality-iMatrix-GGUF overview

Q: How do I run offmonreal/Ornith-1.0-35B-MaxQuality-iMatrix-GGUF locally?

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Ornith 1.0 35B MaxQuality iMatrix GGUF Quality first GGUF quants for running a 35B MoE coding model on consumer hardware. This release aims for the best practi…

ggufllama.cppturboquantqwen35moequantizedimatrixconsumer-gpuoffmorealbase_model:deepreinforce-ai/Ornith-1.0-35Bbase_model:quantized:deepreinforce-ai/Ornith-1.0-35Blicense:mitendpoints_compatibleregion:usconversational

Runs locally from ~16.05 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads

Likes

Pipeline

—

Author

offmonreal

Repository Files & Downloads

2 GGUF files detected

Direct downloads for local inference

File	Type	Quantization	Size	Link
Ornith-1.0-35B-Q3_K_M-iMatrix.gguf	GGUF	Q3_K_M	16.05 GB	Download
Ornith-1.0-35B_Q4_K_M_imatrix.gguf	GGUF	Q4_K_M_IMATRIX	19.71 GB	Download

Model Details

Model ID	offmonreal/Ornith-1.0-35B-MaxQuality-iMatrix-GGUF
Author	offmonreal
Pipeline	—
License	mit
Base model	deepreinforce-ai/Ornith-1.0-35B
Last modified	2026-07-29T21:43:55.000Z

Model README

---

license: mit

base_model: deepreinforce-ai/Ornith-1.0-35B

tags:

- gguf

- llama.cpp

- turboquant

- qwen35moe

- quantized

- imatrix

- consumer-gpu

- offmoreal

---

Ornith-1.0-35B MaxQuality iMatrix GGUF

Quality-first GGUF quants for running a 35B MoE coding model on consumer hardware. This release aims for the best practical balance of output quality, generation speed, and memory use—not merely the smallest possible file.

The vision encoder was removed for a text-only release. The original checkpoint contained 333 model.visual.* tensors; this release contains none.

Files

|---|---:|---:|---|

| Ornith-1.0-35B_Q4_K_M_imatrix.gguf | 19.70 GiB | 4.88 | Higher quality with a balanced MoE CPU/GPU split |

| Ornith-1.0-35B-Q3_K_M-iMatrix.gguf | 16.43 GiB | 3.98 | Quality-focused smaller option for consumer GPUs |

Both files were calibrated with an iMatrix built from calibration_datav5.txt (802 chunks).

Quantization profiles

Q4_K_M iMatrix

Embedding / output: Q6_K
MoE router (ffn_gate_inp): F32
Linear-attention QKV: Q6_K
Full-attention Q/K/output: Q4_K; V: Q6_K
Routed MoE experts: down Q6_K; gate/up Q4_K

Q3 iMatrix

Embedding / output: Q6_K
MoE router (ffn_gate_inp): F32
Linear-attention QKV, gate, and SSM output: Q5_K
Full-attention Q/K/V/output: Q5_K
Shared MoE experts: Q5_K
Routed MoE experts: down Q4_K; gate/up Q3_K
Remaining quantizable tensors: Q3_K_M default

Tested hardware and software

Linux
NVIDIA GeForce RTX 5060 Ti, 16 GB VRAM
AMD Ryzen 9 5950X, 16 cores / 32 threads
64 GB system RAM
TheTom/llama-cpp-turboquant, commit c26cbdffc

Observed generation speed on this machine:

| Variant | Context | Generation speed |

|---|---:|---:|

| Q4 iMatrix | ~10K | ~60 tok/s |

| Q3 iMatrix | first ~10K | ~80 tok/s |

| Q3 iMatrix | ~20K | ~75 tok/s |

Actual speed varies with context length, prompt size, CPU memory bandwidth, and the selected MoE offload split.

Recommended 256K launch commands

These profiles keep the KV cache in VRAM and move only late routed-expert tensors to CPU RAM. Attention, routers, embeddings, and output remain on the GPU. turbo3 KV enables the TurboQuant path; K is automatically upgraded to q8_0 for this model's 8:1 GQA ratio.

Q4: CPU experts in layers 24–39

llama-server \
  --jinja --host 0.0.0.0 --port 8080 \
  -m Ornith-1.0-35B_Q4_K_M_imatrix.gguf \
  --n-gpu-layers 99 --n-cpu-moe 0 \
  -ot "blk\\.(2[4-9]|3[0-9])\\.ffn_.*_exps\\.weight=CPU" \
  --ctx-size 262144 --parallel 1 \
  --flash-attn on \
  --cache-type-k turbo3 --cache-type-v turbo3 \
  --batch-size 2048 --ubatch-size 256 --cache-reuse 256

Q3: CPU experts in layers 30–39

llama-server \
  --jinja --host 0.0.0.0 --port 8080 \
  -m Ornith-1.0-35B-Q3_K_M-iMatrix.gguf \
  --n-gpu-layers 99 --n-cpu-moe 0 \
  -ot "blk\\.3[0-9]\\.ffn_.*_exps\\.weight=CPU" \
  --ctx-size 262144 --parallel 1 \
  --flash-attn on \
  --cache-type-k turbo3 --cache-type-v turbo3 \
  --batch-size 2048 --ubatch-size 256 --cache-reuse 256

The Q3 tested profile leaves approximately 500 MiB VRAM free after allocating a 256K context on the tested 16 GB GPU.

Upstream model card

This release is based on the original Ornith-1.0-35B model card reproduced in full below. Its original license declaration and complete model card are preserved unchanged.

---

library_name: transformers

license: mit

license_link: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE

pipeline_tag: text-generation

---

![Ornith Blog](https://deep-reinforce.com/ornith.html)

Ornith-1.0-35B

Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.

Highlights:

State-of-the-Art Coding Agents: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw.
Self-Improving Training Framework: Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions.
Licence: MIT licensed, globally accessible, and free from regional limitations.

Ornith 1.0 35B

This model card documents Ornith-1.0-35B, the lightweight member of the Ornith family, designed for efficient single-GPU deployment.

Benchmarks

<th style="width:14.40%;padding:10px 7px;text-align:center;font-weight:700;border-bottom:2px solid #FD8E5B;color:#FD8E5B;font-size:14px;background:rgba(253, 142, 91, 0.12)">Ornith-1.0-35B</th>

<th style="width:14.40%;padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #FD8E5B;color:#FD8E5B;font-size:14px">Gemma4-31B</th>

</tr></thead>

<tbody>

<tr><td colspan="6" style="padding:8px 12px;font-weight:600;color:#FD8E5B;border-bottom:1px solid rgba(253, 142, 91, 0.2);background:rgba(253, 142, 91, 0.1)">Agentic Coding</td></tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Terminal-Bench 2.1 <sub><small>(Terminus-2)</small></sub></td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Terminal-Bench 2.1 <sub><small>(Claude Code)</small></sub></td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE-bench Verified</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE-bench Pro</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE-bench Multilingual</td>

</tr>

<tr>

</tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE Atlas - QnA</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE Atlas - RF</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE Atlas - TW</td>

</tr>

</tbody>

</table>

Terminal-Bench 2.1 (Terminus-2): We evaluate Terminal-Bench 2.1 using the Harbor/Terminus-2 framework with parser=json, temperature=1.0, top_p=1.0, and a 128K context window. Each run uses a 4-hour timeout with 32 CPU cores and 48GB RAM, and results are averaged over 5 runs. We adjust the Qwen chat template to ensure consistency between training and inference (https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B/blob/main/chat_template.jinja), and modify Harbor to align with vLLM's reasoning_content key.<br/>
Terminal-Bench 2.1 (Claude Code): We evaluate Terminal-Bench 2.1 using Claude Code 2.1.126 with parser=json, temperature=1.0, top_p=1.0, max_new_tokens=131072. Results are averaged over 5 runs. Again, Qwen chat template needs to be modified.<br/>
SWE-Bench Verified, Pro and Multilingual: using OpenHands harness with temp=1.0, top_p=0.95, 256k context window.<br/>
SWE Atlas QnA, RF, TW: using mini SWE agent harness with temp=1.0, top_p=0.95, 128K context window. Results are averaged over 5 runs.<br/>
NL2Repo: with temperature=1.0, top_p=1.0, 400K context, 48K output and anti-hacking filters.<br/>
ClawEval: An agentic code benchmark over real-user task distributions; temp=0.6 and 256K context.<br/>

</p>

</div>

Quickstart

<p style="margin:0 0 10px"><b>Ornith-1.0-35B</b> is a <b>reasoning model</b>: by default the assistant turn opens with a <code style="background:rgba(253,142,91,0.15);padding:1px 5px;border-radius:4px"><think> … </think></code> block before the final answer. The serving recipes below enable a reasoning parser so the chain-of-thought is returned in a separate <code style="background:rgba(253,142,91,0.15);padding:1px 5px;border-radius:4px">reasoning_content</code> field, and a tool-call parser so the model's <code style="background:rgba(253,142,91,0.15);padding:1px 5px;border-radius:4px"><tool_call></code> blocks are surfaced as OpenAI-style <code style="background:rgba(253,142,91,0.15);padding:1px 5px;border-radius:4px">tool_calls</code>.</p>

<p style="margin:0 0 6px">Serving Ornith-1.0-35B requires recent runtimes:</p>

<li><b>Transformers</b> ≥ 5.8.1</li>

<li><b>SGLang</b> ≥ 0.5.9</li>

</ul>

</div>

Serving Ornith-1.0-35B

The two recipes below stand up an OpenAI-compatible server on a single 8×80GB GPU node (tensor-parallel 8). Adjust --tensor-parallel-size / --tp to the number of GPUs you have.

vLLM

vllm serve deepreinforce-ai/Ornith-1.0-35B \
    --served-model-name Ornith-1.0-35B \
    --tensor-parallel-size 8 \
    --host 0.0.0.0 --port 8000 \
    --max-model-len 262144 \
    --gpu-memory-utilization 0.90 \
    --enable-prefix-caching \
    --enable-auto-tool-choice --tool-call-parser qwen3_xml \
    --reasoning-parser qwen3 \
    --trust-remote-code

SGLang

python -m sglang.launch_server \
    --model-path deepreinforce-ai/Ornith-1.0-35B \
    --served-model-name Ornith-1.0-35B \
    --tp 8 \
    --host 0.0.0.0 --port 8000 \
    --context-length 262144 \
    --mem-fraction-static 0.85 \
    --tool-call-parser qwen3_coder \
    --reasoning-parser qwen3

Hugging Face Transformers

For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-35B requires transformers >= 5.8.1.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "deepreinforce-ai/Ornith-1.0-35B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    dtype="auto",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Write a Python function is_prime(n). Keep it short."}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tokenizer(text, return_tensors="pt").to(model.device)
generated = model.generate(
    **inputs,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.6,
    top_p=0.95,
    top_k=20,
)
output_ids = generated[0][inputs.input_ids.shape[1]:]

# The reply contains a <think> ... </think> reasoning block followed by the answer.
content = tokenizer.decode(output_ids, skip_special_tokens=True)
print(content)

To split the reasoning trace from the final answer, parse on the </think> marker:

text = tokenizer.decode(output_ids, skip_special_tokens=True)
if "</think>" in text:
    reasoning, answer = text.split("</think>", 1)
    reasoning = reasoning.replace("<think>", "").strip()
    answer = answer.strip()
else:
    reasoning, answer = "", text.strip()

Using Ornith-1.0-35B via the Chat Completions API

Once a vLLM or SGLang server is running, talk to it with any OpenAI-compatible client.

Basic Usage

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY",  # any non-empty string works for a local server
)

response = client.chat.completions.create(
    model="Ornith-1.0-35B",
    messages=[
        {"role": "user", "content": "Write a one-line Python lambda that squares a number."}
    ],
    temperature=0.6,
    top_p=0.95,
    max_tokens=1024,
)

message = response.choices[0].message
# reasoning_content holds the <think> trace; content holds the final answer.
print("reasoning:", getattr(message, "reasoning_content", None))
print("answer:", message.content)

You can also stream tokens, or hand the model tools — Ornith-1.0-35B emits well-formed function calls that the server parses into the standard tool_calls field:

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a city",
            "parameters": {
                "type": "object",
                "properties": {"city": {"type": "string"}},
                "required": ["city"],
            },
        },
    }
]

response = client.chat.completions.create(
    model="Ornith-1.0-35B",
    messages=[{"role": "user", "content": "What is the weather in Paris right now?"}],
    tools=tools,
    tool_choice="auto",
    temperature=0.6,
    max_tokens=2048,
)

tool_call = response.choices[0].message.tool_calls[0]
print(tool_call.function.name, tool_call.function.arguments)
# -> get_weather {"city": "Paris"}

You can point any OpenAI-compatible SDK (Python, Node.js, etc.) or curl at the same /v1/chat/completions endpoint.

Agentic Usage

Ornith-1.0-35B excels in tool-calling and agentic coding capabilities.

Agent Frameworks

Because Ornith-1.0-35B exposes an OpenAI-compatible endpoint with tool calling, it works out of the box with standard agent frameworks. Below is a minimal example that connects Ornith-1.0-35B to tools through an MCP server.

import os
from openai import OpenAI

client = OpenAI(
    base_url=os.getenv("OPENAI_BASE_URL", "http://localhost:8000/v1"),
    api_key=os.getenv("OPENAI_API_KEY", "EMPTY"),
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "run_shell",
            "description": "Run a shell command and return its output.",
            "parameters": {
                "type": "object",
                "properties": {
                    "command": {"type": "string", "description": "The command to run"}
                },
                "required": ["command"],
            },
        },
    }
]

messages = [{"role": "user", "content": "List the Python files in the current directory."}]

response = client.chat.completions.create(
    model="deepreinforce-ai/Ornith-1.0-35B",
    messages=messages,
    tools=tools,
    temperature=0.6,
    top_p=0.95,
)
print(response.choices[0].message)

Examples of using Ornith with agent harness:

Hermes Agent

# Hermes talks to any OpenAI-compatible endpoint — point it at your Ornith server.
export OPENAI_BASE_URL="http://localhost:8000/v1"
export OPENAI_API_KEY="EMPTY"
export MODEL="deepreinforce-ai/Ornith-1.0-35B"

Atomic.chat/ Ollama / llama.cpp

# Both runtimes load a GGUF build of Ornith (publish one at deepreinforce-ai/Ornith-1.0-35B-GGUF).

# llama.cpp — serve an OpenAI-compatible API on port 8000.
llama-server -hf deepreinforce-ai/Ornith-1.0-35B-GGUF --port 8000 -c 262144

# Ollama — pull and chat with the same GGUF straight from Hugging Face.
ollama run hf.co/deepreinforce-ai/Ornith-1.0-35B-GGUF

OpenClaw

# OpenClaw talks to any OpenAI-compatible endpoint — point it at your Ornith server.
export OPENAI_BASE_URL="http://localhost:8000/v1"
export OPENAI_API_KEY="EMPTY"
export OPENAI_MODEL="deepreinforce-ai/Ornith-1.0-35B"

Unsloth Studio

pip install unsloth

# Load Ornith for fast local inference or fine-tuning (Python):
#   from unsloth import FastLanguageModel
#   model, tokenizer = FastLanguageModel.from_pretrained(
#       "deepreinforce-ai/Ornith-1.0-35B",
#       max_seq_length=262144,
#       load_in_4bit=True,
#   )

OpenHands

pip install openhands-ai

# OpenHands routes through LiteLLM; the "openai/" prefix selects the OpenAI-compatible path.
export LLM_MODEL="openai/deepreinforce-ai/Ornith-1.0-35B"
export LLM_BASE_URL="http://localhost:8000/v1"
export LLM_API_KEY="EMPTY"

# Launch the CLI (or run the official OpenHands Docker image with the same env vars).
openhands

Coding CLIs

Ornith-1.0-35B is optimized for terminal-based coding agents. Point any OpenAI-compatible coding CLI at your Ornith-1.0-35B endpoint (set OPENAI_BASE_URL and OPENAI_API_KEY) to understand large codebases, automate tedious work, and ship faster.

OpenCode

# Register your local Ornith endpoint as a provider in ~/.config/opencode/opencode.json:
#
# {
#   "$schema": "https://opencode.ai/config.json",
#   "provider": {
#     "ornith": {
#       "npm": "@ai-sdk/openai-compatible",
#       "name": "Ornith (local)",
#       "options": { "baseURL": "http://localhost:8000/v1", "apiKey": "EMPTY" },
#       "models": { "deepreinforce-ai/Ornith-1.0-35B": { "name": "Ornith-1.0-35B" } }
#     }
#   }
# }

opencode

Citation

If you find our work helpful, feel free to give us a cite.

@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}
}

Run offmonreal/Ornith-1.0-35B-MaxQuality-iMatrix-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models