mlx-community / Ornith-1.0-35B-4bit

huggingface.co
Total runs: 2.0K
24-hour runs: 0
7-day runs: -1.1K
30-day runs: -9.3K
Model's Last Updated: June 28 2026
image-text-to-text

Introduction of Ornith-1.0-35B-4bit

Model Details of Ornith-1.0-35B-4bit

Ornith-1.0-35B-4bit

4-bit (group size 64, 4.649 bits/weight ) MLX quantization of deepreinforce-ai/Ornith-1.0-35B , produced with mlx-vlm 0.6.3. Full multimodal: the vision encoder is preserved and quantized alongside the language model. For Apple Silicon. Runs in mlx-vlm or any MLX app.

Conversion note (MoE expert fusion)

Ornith stores its 256 MoE experts unfused (per-expert), but mlx-vlm's qwen3_5_moe loader expects them fused/batched. A sanitize monkeypatch was required to stack the experts before conversion; without it the conversion failed. This is a standard mlx-vlm 4-bit quant.

Usage
uvx --from mlx-vlm mlx_vlm.generate \
  --model mlx-community/Ornith-1.0-35B-4bit --image image.png \
  --prompt "Describe this image." --max-tokens 512
from mlx_vlm import load, generate
model, processor = load("mlx-community/Ornith-1.0-35B-4bit")
Conversion check

Smoke-tested after conversion (text-only prompt, mlx_vlm.generate ): coherent — solved 17 * 24 = 408 with correct step-by-step reasoning, no repetition loop. 103.7 tok/s generation, 89.4 tok/s prompt, peak 20.9 GB on a Macbook Pro M5 Max 128GB 40 GPU.

Refer to the original model card for architecture, benchmarks, license, and intended use.

Runs of mlx-community Ornith-1.0-35B-4bit on huggingface.co

2.0K
Total runs
0
24-hour runs
-388
3-day runs
-1.1K
7-day runs
-9.3K
30-day runs

More Information About Ornith-1.0-35B-4bit huggingface.co Model

More Ornith-1.0-35B-4bit license Visit here:

https://choosealicense.com/licenses/mit

Ornith-1.0-35B-4bit huggingface.co

Ornith-1.0-35B-4bit huggingface.co is an AI model on huggingface.co that provides Ornith-1.0-35B-4bit's model effect (), which can be used instantly with this mlx-community Ornith-1.0-35B-4bit model. huggingface.co supports a free trial of the Ornith-1.0-35B-4bit model, and also provides paid use of the Ornith-1.0-35B-4bit. Support call Ornith-1.0-35B-4bit model through api, including Node.js, Python, http.

mlx-community Ornith-1.0-35B-4bit online free

Ornith-1.0-35B-4bit huggingface.co is an online trial and call api platform, which integrates Ornith-1.0-35B-4bit's modeling effects, including api services, and provides a free online trial of Ornith-1.0-35B-4bit, you can try Ornith-1.0-35B-4bit online for free by clicking the link below.

mlx-community Ornith-1.0-35B-4bit online free url in huggingface.co:

https://huggingface.co/mlx-community/Ornith-1.0-35B-4bit

Ornith-1.0-35B-4bit install

Ornith-1.0-35B-4bit is an open source model from GitHub that offers a free installation service, and any user can find Ornith-1.0-35B-4bit on GitHub to install. At the same time, huggingface.co provides the effect of Ornith-1.0-35B-4bit install, users can directly use Ornith-1.0-35B-4bit installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Ornith-1.0-35B-4bit install url in huggingface.co:

https://huggingface.co/mlx-community/Ornith-1.0-35B-4bit

Url of Ornith-1.0-35B-4bit

Ornith-1.0-35B-4bit huggingface.co Url

Provider of Ornith-1.0-35B-4bit huggingface.co

mlx-community
ORGANIZATIONS

Other API from mlx-community