Instructions to use jedisct1/Ornith-DOTResize-448-MLX-oQ8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jedisct1/Ornith-DOTResize-448-MLX-oQ8 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("jedisct1/Ornith-DOTResize-448-MLX-oQ8")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use jedisct1/Ornith-DOTResize-448-MLX-oQ8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jedisct1/Ornith-DOTResize-448-MLX-oQ8"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jedisct1/Ornith-DOTResize-448-MLX-oQ8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use jedisct1/Ornith-DOTResize-448-MLX-oQ8 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "jedisct1/Ornith-DOTResize-448-MLX-oQ8"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "jedisct1/Ornith-DOTResize-448-MLX-oQ8"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "jedisct1/Ornith-DOTResize-448-MLX-oQ8",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use jedisct1/Ornith-DOTResize-448-MLX-oQ8 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jedisct1/Ornith-DOTResize-448-MLX-oQ8"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jedisct1/Ornith-DOTResize-448-MLX-oQ8

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jedisct1/Ornith-DOTResize-448-MLX-oQ8 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jedisct1/Ornith-DOTResize-448-MLX-oQ8"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "jedisct1/Ornith-DOTResize-448-MLX-oQ8" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Ornith-DOTResize-448-MLX-oQ8 / README.md

jedisct1

Update model card wording

c7bc211 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

2.06 kB

metadata

license: mit
base_model: deepreinforce-ai/Ornith-1.0-35B
library_name: mlx
pipeline_tag: text-generation
tags:
  - mlx
  - qwen3.5-moe
  - vision-language
  - tool-use
  - dotresize
  - 8-bit

Ornith DOTResize 448 MLX oQ8

This is the oQ8 MLX quantized build, using affine group-size-64 quantization. The measured local artifact size is about 31 GiB. It is derived from deepreinforce-ai/Ornith-1.0-35B at revision 5df2ed3f675c7beaa490328cc70bb573b65fb660.

The model keeps the Qwen3.5-MoE/VLM structure and tokenizer/tool template, but reduces the MoE intermediate width from 512 to 448 with a support-preserving DOTResize pass. The goal of this build is to keep the 262k context metadata, coding behavior, and OpenAI-compatible tool calling while shaving memory from the original 35B BF16 artifact.

Thinking is disabled unless a runtime explicitly supplies enable_thinking=true, which prevents normal chat responses from exposing <think> delimiters or other internal wrapper tokens. The tool template is still present for runtimes that parse structured tool calls.

Variants

BF16: jedisct1/Ornith-DOTResize-448-MLX-BF16
oQ8: jedisct1/Ornith-DOTResize-448-MLX-oQ8
oQ4: jedisct1/Ornith-DOTResize-448-MLX-oQ4

Local Validation

Before upload, the BF16 artifact passed static MLX safetensor inspection, oMLX lazy load, LM Studio load at 262144 context, direct OpenAI-compatible tool-call smoke, Swival core and all-tools gates at 5/5 with zero failed tool calls, a coding smoke, and a long-context retrieval smoke at 241,934 prompt tokens.

The oQ8 and oQ4 artifacts were produced with oMLX streaming oQ quantization using text_only=false, then checked for VLM metadata preservation, quantized safetensor structure, oMLX lazy load, LM Studio load, direct tool-call behavior, and absence of visible thinking/tool wrapper tokens.

Notes

This is a derived local conversion and reduction, not a new base model. The validation above is practical smoke and integration coverage, not a replacement for a benchmark suite.