Instructions to use nightmedia/Qwen3-Coder-Next-qx53n-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nightmedia/Qwen3-Coder-Next-qx53n-mlx 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("nightmedia/Qwen3-Coder-Next-qx53n-mlx")

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 nightmedia/Qwen3-Coder-Next-qx53n-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nightmedia/Qwen3-Coder-Next-qx53n-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nightmedia/Qwen3-Coder-Next-qx53n-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nightmedia/Qwen3-Coder-Next-qx53n-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nightmedia/Qwen3-Coder-Next-qx53n-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nightmedia/Qwen3-Coder-Next-qx53n-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nightmedia/Qwen3-Coder-Next-qx53n-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use nightmedia/Qwen3-Coder-Next-qx53n-mlx 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 "nightmedia/Qwen3-Coder-Next-qx53n-mlx"

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 nightmedia/Qwen3-Coder-Next-qx53n-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nightmedia/Qwen3-Coder-Next-qx53n-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nightmedia/Qwen3-Coder-Next-qx53n-mlx"

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 "nightmedia/Qwen3-Coder-Next-qx53n-mlx" \
  --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"

nightmedia commited on Feb 10

Commit

a96200b

verified ·

1 Parent(s): 52aca9b

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -0

README.md CHANGED Viewed

@@ -52,6 +52,27 @@ The mxfp8 seems unbeatable in speed, and its metrics are excellent, showing high
 ---
 Here are some Brainwaves for qx86-hi for Nightmedia 30B-A3B elements, to give an idea how much better Next could be
 These tests have nothing to do with what the model knows, but how well it thinks with what it knows.

 ---
+# REAP models
+I benchmarked the mxfp8 for being the most stable quant with very little loss from full precision.
+```brainwave
+Qwen3-Coder-Next
+mxfp8  0.514,0.709,0.884,0.639,0.420,0.748,0.611
+lovedheart/Qwen3-Coder-Next-REAP-40B-A3B
+mxfp8  0.390,0.508,0.610,0.532,0.354,0.665,0.577
+Mattepiu/Qwen3-Coder-Next-REAP-48B-A3B
+mxfp8  pending
+```
+The REAP models seem much more cheerful than the original, but lose a lot of arc and boolq that shows as heavy hallucinations in the output.
+---
+# Nightmedia models
 Here are some Brainwaves for qx86-hi for Nightmedia 30B-A3B elements, to give an idea how much better Next could be
 These tests have nothing to do with what the model knows, but how well it thinks with what it knows.