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

File	Size	BPW	Intended use
`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

bash

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

bash

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-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

	Ornith-1.0-35B	Qwen3.5-35B	Qwen3.6-35B	Gemma4-31B	Qwen3.5-397B
Agentic Coding
Terminal-Bench 2.1 _(Terminus-2)	64.2	41.4	52.5	42.1	53.5
Terminal-Bench 2.1 _{(Claude Code)}	62.8	38.9	49.2	-	48.6
SWE-bench Verified	75.6	70	73.4	52	76.4
SWE-bench Pro	50.4	44.6	49.5	35.7	51.6
SWE-bench Multilingual	69.3	60.3	67.2	51.7	69.3
NL2Repo	34.6	20.5	29.4	15.5	36.8
Claw-eval Avg	69.8	65.4	68.7	48.5	70.7
SWE Atlas - QnA	37.1	13.2	15.5	-	20.4
SWE Atlas - RF	29.7	10.2	11.4	-	18.4
SWE Atlas - TW	27.8	9.8	13.3	-	18.5

* 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.
* 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.
* SWE-Bench Verified, Pro and Multilingual: using OpenHands harness with temp=1.0, top_p=0.95, 256k context window.
* 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.
* NL2Repo: with temperature=1.0, top_p=1.0, 400K context, 48K output and anti-hacking filters.
* ClawEval: An agentic code benchmark over real-user task distributions; temp=0.6 and 256K context.

Quickstart

📝 NOTE

Ornith-1.0-35B is a reasoning model: by default the assistant turn opens with a <think> … </think> block before the final answer. The serving recipes below enable a reasoning parser so the chain-of-thought is returned in a separate reasoning_content field, and a tool-call parser so the model's <tool_call> blocks are surfaced as OpenAI-style tool_calls.

Serving Ornith-1.0-35B requires recent runtimes:

Transformers ≥ 5.8.1
vLLM ≥ 0.19.1
SGLang ≥ 0.5.9

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

bash

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

bash

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.

python

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:

python

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

python

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:

python

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.

python

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

bash

# 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

bash

# 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

bash

# 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

bash

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

bash

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

bash

# 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.

bibtex

@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}
}

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

Ornith-1.0-35B MaxQuality iMatrix GGUF

Files

Quantization profiles

Q4_K_M iMatrix

Q3 iMatrix

Tested hardware and software

Recommended 256K launch commands

Q4: CPU experts in layers 24–39

Q3: CPU experts in layers 30–39

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-1.0-35B

Ornith 1.0 35B

Benchmarks

Quickstart

Serving Ornith-1.0-35B

vLLM

SGLang

Hugging Face Transformers

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

Basic Usage

Agentic Usage

Agent Frameworks

Hermes Agent

Atomic.chat/ Ollama / llama.cpp

OpenClaw

Unsloth Studio

OpenHands

Coding CLIs

OpenCode

Citation

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