Instructions to use sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit 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("sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit")

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 sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit"

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": "sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit"

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 "sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit" \
  --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"

MLX LM

How to use sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit 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 "sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit"

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 sjug/Qwen3-235B-A22B-Thinking-2507-MLX-9bit

Run Hermes

hermes

sjug commited on Jul 26, 2025

Commit

b1c394a

verified ·

1 Parent(s): 0b7b814

Add files using upload-large-folder tool

Browse files

Files changed (18) hide show

model-00001-of-00057.safetensors +3 -0
model-00005-of-00057.safetensors +3 -0
model-00008-of-00057.safetensors +3 -0
model-00012-of-00057.safetensors +3 -0
model-00015-of-00057.safetensors +3 -0
model-00017-of-00057.safetensors +3 -0
model-00018-of-00057.safetensors +3 -0
model-00020-of-00057.safetensors +3 -0
model-00021-of-00057.safetensors +3 -0
model-00025-of-00057.safetensors +3 -0
model-00029-of-00057.safetensors +3 -0
model-00032-of-00057.safetensors +3 -0
model-00038-of-00057.safetensors +3 -0
model-00041-of-00057.safetensors +3 -0
model-00044-of-00057.safetensors +3 -0
model-00048-of-00057.safetensors +3 -0
model-00053-of-00057.safetensors +3 -0
model-00056-of-00057.safetensors +3 -0

+version https://git-lfs.github.com/spec/v1
+oid sha256:56bd3753e22b925e871c86a07928729eed9ec06157ac40a3ef8d781ce6574886
+size 5341289768

+version https://git-lfs.github.com/spec/v1
+oid sha256:37f2ab4c3670f0eff55d2bf63fe5fba35e8b763549075337073615574bea14c2
+size 4691500108

+version https://git-lfs.github.com/spec/v1
+oid sha256:6deb9aa68ca81e84e4e144bcd191f14e96995ea86252c766abddb8b540bbf22e
+size 4691500143

+version https://git-lfs.github.com/spec/v1
+oid sha256:76f2236fbfbfb14499ee1e0b4da081b7657c94b66407f7bc680a9a5a8dfee435
+size 4691500127

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5173ccc4601687fae3eb63e511a35a852e3a1ec7cb0c1bc347d7b61bc0158f9
+size 4691500109

+version https://git-lfs.github.com/spec/v1
+oid sha256:0d219d245b8e6d5d57c573ab2874adf3f119c67a0af51846122927f287bc6a39
+size 4691500131

+version https://git-lfs.github.com/spec/v1
+oid sha256:643f392c9147d33702e43f9af85a4fb73b41515dbfcfa6ffd7c2a1686f1596af
+size 4691500139

+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9635fb8c4ed10c4a5b6548e559ec69bf3268fbc8bd03adb2821eb512f89885
+size 4691500117

+version https://git-lfs.github.com/spec/v1
+oid sha256:972541f52c6a565ddfaec5d4683378c8ea09d1e0d22e657c00d83f9562a2fbfb
+size 4610675219

+version https://git-lfs.github.com/spec/v1
+oid sha256:321531271d097fe80765b89582c3457e6143c1748f367487967b0102121e3ca3
+size 4691500169

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:61c20717c37aab316abcb86e7bd21594b3b6cc4022f20f799207d1c8dc22cbf7
+size 4691500173

+version https://git-lfs.github.com/spec/v1
+oid sha256:3594f6bda198e93af8c0310d3663140685a4fb263b1dfccee7a1bb69b7d8e383
+size 4691500161

+version https://git-lfs.github.com/spec/v1
+oid sha256:959723c26ddb76923b3ca3be9652bbe2783f21e59911eed77c87b4c8a212b8f9
+size 4691500185

+version https://git-lfs.github.com/spec/v1
+oid sha256:bcedc96681b768c8c5fcde5ed15961f1fa65f7cfab95ba70eddc3b2e8936e826
+size 4691500165

+version https://git-lfs.github.com/spec/v1
+oid sha256:30f593bfa56ac0840713e03c507292fb4768f21523b84ed8691a219b2c0a5947
+size 4691500099

+version https://git-lfs.github.com/spec/v1
+oid sha256:12a48d9d436edacaf96a9a1f5c5efae77f7d7367b59b02d1e8323c8f805e83e2
+size 4691500157