Instructions to use mlx-community/Qwen3.5-9B-OptiQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Qwen3.5-9B-OptiQ-4bit 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("mlx-community/Qwen3.5-9B-OptiQ-4bit")

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 mlx-community/Qwen3.5-9B-OptiQ-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Qwen3.5-9B-OptiQ-4bit"

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": "mlx-community/Qwen3.5-9B-OptiQ-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use mlx-community/Qwen3.5-9B-OptiQ-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Qwen3.5-9B-OptiQ-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Qwen3.5-9B-OptiQ-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Qwen3.5-9B-OptiQ-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use mlx-community/Qwen3.5-9B-OptiQ-4bit 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 "mlx-community/Qwen3.5-9B-OptiQ-4bit"

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 mlx-community/Qwen3.5-9B-OptiQ-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/Qwen3.5-9B-OptiQ-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Qwen3.5-9B-OptiQ-4bit"

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 "mlx-community/Qwen3.5-9B-OptiQ-4bit" \
  --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"

codelion commited on Jul 14

Commit

804d898

verified ·

1 Parent(s): 1f7c283

Correct BFCL + Capability: the AST checker could not match array-typed arguments

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -84,10 +84,10 @@ Six-metric Capability Score (mean of MMLU + GSM8K + IFEval + BFCL + HumanEval +
 | MMLU (5-shot, 1000 samples) | **69.1%** | 68.6% | +0.5 |
 | GSM8K (1000 samples, 3-shot CoT) | **81.7%** | 81.7% | +0.0 |
 | IFEval (full set, strict) | **71.2%** | 71.0% | +0.2 |
-| BFCL-V3 simple (200 calls) | **72.5%** | 73.5% | -1.0 |
 | HumanEval (164 problems, pass@1) | **81.1%** | 78.7% | +2.4 |
 | HashHop (long-context retrieval) | **25.0%** | 26.0% | -1.0 |
-| **Capability Score** (mean of 6) | **66.77** | 66.58 | **+0.19** |
 | KL vs uniform-4-bit reference (mean / p95) | 0.1937 / 1.0790 |, |, |
 | On-disk size | 6.6 GB | 5.5 GB | +1.1 |

 | MMLU (5-shot, 1000 samples) | **69.1%** | 68.6% | +0.5 |
 | GSM8K (1000 samples, 3-shot CoT) | **81.7%** | 81.7% | +0.0 |
 | IFEval (full set, strict) | **71.2%** | 71.0% | +0.2 |
+| BFCL-V3 simple (200 calls) | **91.0%** | 92.0% | -1.0 |
 | HumanEval (164 problems, pass@1) | **81.1%** | 78.7% | +2.4 |
 | HashHop (long-context retrieval) | **25.0%** | 26.0% | -1.0 |
+| **Capability Score** (mean of 6) | **69.85** | 69.66 | **+0.19** |
 | KL vs uniform-4-bit reference (mean / p95) | 0.1937 / 1.0790 |, |, |
 | On-disk size | 6.6 GB | 5.5 GB | +1.1 |