AtomicChat / Ornith-9B-MLX-6bit

huggingface.co
Total runs: 136
24-hour runs: -9
7-day runs: -54
30-day runs: -818
Model's Last Updated: July 23 2026
text-generation

Introduction of Ornith-9B-MLX-6bit

Model Details of Ornith-9B-MLX-6bit


Ornith 1.0 9B

Ornith 1.0 9B , quantized to MLX 6-bit by Atomic Chat for Apple Silicon. Built straight from DeepReinforce's original weights. Runs fully offline on your Mac.

Highlights
  • A self-improving open-source family for agentic coding from DeepReinforce, built for tool-calling and terminal-based coding agents.
  • Post-trained on top of Gemma 4 and Qwen 3.5 , the smallest, fastest member of the Ornith 1.0 lineup.
  • Strong agentic coding scores for its size : 69.4 on SWE-bench Verified and 43.1 on Terminal-Bench 2.1 (Terminus-2).
  • Dense architecture, 32 layers , qwen3_5 model type with a hidden_size of 4096.
  • 262,144-token native context for long files and multi-step agent traces.
  • Pure open : MIT licensed, globally accessible with no regional limits.
  • Full quant ladder with an importance matrix on every quant over calibration_datav3 .

This is the MLX 6-bit build for Apple Silicon (M-series). For llama.cpp/Ollama/CPU use the GGUF repo .

Model Overview
Property Value
Base model deepreinforce-ai/Ornith-1.0-9B
Total parameters ~9B (model name; card states no exact figure in prose)
Layers 32
Context length 262,144
Architecture qwen3_5 dense causal LM, post-trained on Gemma 4 and Qwen 3.5
This repo MLX 6-bit quant for Apple Silicon (~7.3 GB), built from the original weights.
Ornith 1.0 9B benchmarks

Scores are DeepReinforce's published results for the full-precision base deepreinforce-ai/Ornith-1.0-9B . MLX quants run the same model locally; lower bit-widths trade a little accuracy for size/speed.

MLX quants in this series

4-bit · 5-bit · 6-bit ← this · 8-bit

Run on Apple Silicon
pip install mlx-lm
mlx_lm.generate --model AtomicChat/ornith-9b-MLX-6bit --prompt "Write a quicksort in Python" --max-tokens 512
from mlx_lm import load, generate
model, tokenizer = load("AtomicChat/ornith-9b-MLX-6bit")
msg = [{"role": "user", "content": "Write a quicksort in Python"}]
prompt = tokenizer.apply_chat_template(msg, add_generation_prompt=True)
print(generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True))

Or open it in Atomic Chat : search AtomicChat/ornith-9b-MLX-6bit and hit Use this model .

Recommended sampling
Parameter Value
temperature 0.6
top_p 0.95
top_k 20

DeepReinforce's recommended sampling parameters. The card notes that temperature=1.0 reproduces the reported benchmark setup.

How this was made
  1. Download deepreinforce-ai/Ornith-1.0-9B (original weights).
  2. Convert + quantize to MLX with mlx_lm.convert -q --q-bits 6 --q-group-size 64 .
License

Released by DeepReinforce under the MIT license, globally accessible with no regional limits. Quantized to MLX by Atomic Chat.

Runs of AtomicChat Ornith-9B-MLX-6bit on huggingface.co

136
Total runs
-9
24-hour runs
-27
3-day runs
-54
7-day runs
-818
30-day runs

More Information About Ornith-9B-MLX-6bit huggingface.co Model

More Ornith-9B-MLX-6bit license Visit here:

https://choosealicense.com/licenses/mit

Ornith-9B-MLX-6bit huggingface.co

Ornith-9B-MLX-6bit huggingface.co is an AI model on huggingface.co that provides Ornith-9B-MLX-6bit's model effect (), which can be used instantly with this AtomicChat Ornith-9B-MLX-6bit model. huggingface.co supports a free trial of the Ornith-9B-MLX-6bit model, and also provides paid use of the Ornith-9B-MLX-6bit. Support call Ornith-9B-MLX-6bit model through api, including Node.js, Python, http.

Ornith-9B-MLX-6bit huggingface.co Url

https://huggingface.co/AtomicChat/Ornith-9B-MLX-6bit

AtomicChat Ornith-9B-MLX-6bit online free

Ornith-9B-MLX-6bit huggingface.co is an online trial and call api platform, which integrates Ornith-9B-MLX-6bit's modeling effects, including api services, and provides a free online trial of Ornith-9B-MLX-6bit, you can try Ornith-9B-MLX-6bit online for free by clicking the link below.

AtomicChat Ornith-9B-MLX-6bit online free url in huggingface.co:

https://huggingface.co/AtomicChat/Ornith-9B-MLX-6bit

Ornith-9B-MLX-6bit install

Ornith-9B-MLX-6bit is an open source model from GitHub that offers a free installation service, and any user can find Ornith-9B-MLX-6bit on GitHub to install. At the same time, huggingface.co provides the effect of Ornith-9B-MLX-6bit install, users can directly use Ornith-9B-MLX-6bit installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Ornith-9B-MLX-6bit install url in huggingface.co:

https://huggingface.co/AtomicChat/Ornith-9B-MLX-6bit

Url of Ornith-9B-MLX-6bit

Ornith-9B-MLX-6bit huggingface.co Url

Provider of Ornith-9B-MLX-6bit huggingface.co

AtomicChat
ORGANIZATIONS

Other API from AtomicChat

huggingface.co

Total runs: 395
Run Growth: -576
Growth Rate: -145.82%
Updated:July 23 2026
huggingface.co

Total runs: 32
Run Growth: -40
Growth Rate: -125.00%
Updated:July 28 2026