Instructions to use alan13367/Qwen3.5-4B-RustCoder-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alan13367/Qwen3.5-4B-RustCoder-MLX-8bit 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("alan13367/Qwen3.5-4B-RustCoder-MLX-8bit")

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 alan13367/Qwen3.5-4B-RustCoder-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "alan13367/Qwen3.5-4B-RustCoder-MLX-8bit"

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": "alan13367/Qwen3.5-4B-RustCoder-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use alan13367/Qwen3.5-4B-RustCoder-MLX-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "alan13367/Qwen3.5-4B-RustCoder-MLX-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "alan13367/Qwen3.5-4B-RustCoder-MLX-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "alan13367/Qwen3.5-4B-RustCoder-MLX-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use alan13367/Qwen3.5-4B-RustCoder-MLX-8bit 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 "alan13367/Qwen3.5-4B-RustCoder-MLX-8bit"

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 alan13367/Qwen3.5-4B-RustCoder-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use alan13367/Qwen3.5-4B-RustCoder-MLX-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "alan13367/Qwen3.5-4B-RustCoder-MLX-8bit"

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 "alan13367/Qwen3.5-4B-RustCoder-MLX-8bit" \
  --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"

alan13367 commited on about 16 hours ago

Commit

225e85b

verified ·

1 Parent(s): c287d65

Card: renamed to -MLX-8bit, link to the bf16 version

Browse files

Files changed (1) hide show

README.md +8 -6

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
-base_model: Qwen/Qwen3.5-4B
-base_model_relation: finetune
 library_name: mlx
 license: apache-2.0
 pipeline_tag: text-generation
@@ -15,9 +15,11 @@ tags:
   - 8bit
 ---
-# Qwen3.5-4B-RustCoder
-[Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) fine-tuned to write Rust that compiles, passes tests and is clippy-clean. It keeps its thinking mode. It is an MLX checkpoint for Apple Silicon, 8-bit (group size 64), with the LoRA merged into the weights of [mlx-community/Qwen3.5-4B-MLX-8bit](https://huggingface.co/mlx-community/Qwen3.5-4B-MLX-8bit).
 Every training answer was checked by a gate that builds the code, runs hidden tests and lints it. Answers that failed it were not used.
@@ -50,7 +52,7 @@ With [mlx-vlm](https://github.com/Blaizzy/mlx-vlm) (the checkpoint keeps the bas
 ```bash
 pip install -U mlx-vlm
-python -m mlx_vlm.generate --model alan13367/Qwen3.5-4B-RustCoder --enable-thinking \
   --max-tokens 4096 --temperature 0.6 --top-p 0.95 --top-k 20 \
   --prompt "Write in Rust: pub fn median(xs: &mut [i64]) -> Option<f64>"
 ```
@@ -58,7 +60,7 @@ python -m mlx_vlm.generate --model alan13367/Qwen3.5-4B-RustCoder --enable-think
 ```python
 from mlx_vlm import load, generate
-model, processor = load("alan13367/Qwen3.5-4B-RustCoder")
 messages = [{"role": "user", "content": "Write in Rust: pub fn median(xs: &mut [i64]) -> Option<f64>"}]
 prompt = processor.tokenizer.apply_chat_template(
     messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)

 ---
+base_model: alan13367/Qwen3.5-4B-RustCoder
+base_model_relation: quantized
 library_name: mlx
 license: apache-2.0
 pipeline_tag: text-generation
   - 8bit
 ---
+# Qwen3.5-4B-RustCoder-MLX-8bit
+[Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) fine-tuned to write Rust that compiles, passes tests and is clippy-clean. It keeps its thinking mode. This is the MLX checkpoint for Apple Silicon, 8-bit (group size 64), with the LoRA merged into the weights of [mlx-community/Qwen3.5-4B-MLX-8bit](https://huggingface.co/mlx-community/Qwen3.5-4B-MLX-8bit). It is the checkpoint that was trained and evaluated.
+For transformers and other non-MLX tools, use the bf16 safetensors version: [alan13367/Qwen3.5-4B-RustCoder](https://huggingface.co/alan13367/Qwen3.5-4B-RustCoder).
 Every training answer was checked by a gate that builds the code, runs hidden tests and lints it. Answers that failed it were not used.
 ```bash
 pip install -U mlx-vlm
+python -m mlx_vlm.generate --model alan13367/Qwen3.5-4B-RustCoder-MLX-8bit --enable-thinking \
   --max-tokens 4096 --temperature 0.6 --top-p 0.95 --top-k 20 \
   --prompt "Write in Rust: pub fn median(xs: &mut [i64]) -> Option<f64>"
 ```
 ```python
 from mlx_vlm import load, generate
+model, processor = load("alan13367/Qwen3.5-4B-RustCoder-MLX-8bit")
 messages = [{"role": "user", "content": "Write in Rust: pub fn median(xs: &mut [i64]) -> Option<f64>"}]
 prompt = processor.tokenizer.apply_chat_template(
     messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)