Skip to content

Qwen

Qwen/Qwen3-4B

Dense 4B chat model with mlxcel thinking, tool-calling, and KV-cache controls.

Start this recipeView on Hugging Face
Model metadata
CategoryDenseParams4.02BContext40,960BackendsCUDA, METALTasksChat, Reasoning, Tool calling
Recipe authorship · Recorded configuration verification

Recipe authorship: Curated

Curated and generated describe how this recipe was written, not whether it ran successfully.

Recorded configuration verification

No current matching configuration verification record.

Records cover the tested default configuration on the named hardware. Matching release minor, variant, and rendering hash are required; changing options does not verify the new configuration.

Choose your actual device. Your browser cannot detect GPU memory.

Command builder

Hardware
Variant

mlx-community/Qwen3-4B-4bit

Mode: Server
Advanced
Mode
Context

Context length is measured in tokens. Use the slider or enter a number.

Slots
Features
This feature is not available in the selected mode.
Memory estimation: Why unavailable?

This feature is not available in the selected mode.

Estimated memory use

approx

Approximate memory allocation in GB. These estimates are not measured peak usage.

  • Weights: ≈ 2.1 GB
  • KV: ≈ 1.1 GB
  • Drafter: ≈ 0.0 GB
  • Runtime allowance: ≈ 1.3 GB

Estimated to leave ≈ 11.5 GB of the ≈ 16.1 GB available memory.

Next: prepare the executable

Notes

  • This tier is estimated from nearby measurements.

1. Install

Install in your terminal. Uncached model IDs download automatically on first use.

MLXCEL_INSTALL_DIR="${MLXCEL_INSTALL_DIR:-$HOME/.local/share/mlxcel}" \
  && mkdir -p "$MLXCEL_INSTALL_DIR" \
  && curl -fL -o "$MLXCEL_INSTALL_DIR/mlxcel.zip" https://github.com/lablup/mlxcel/releases/download/v0.8.1/mlxcel-macos-aarch64.zip \
  && unzip -o "$MLXCEL_INSTALL_DIR/mlxcel.zip" -d "$MLXCEL_INSTALL_DIR/mlxcel-macos-aarch64" \
  && export PATH="$MLXCEL_INSTALL_DIR/mlxcel-macos-aarch64:$PATH" \
  && mlxcel --version
Installation and download help

Run the install command in your terminal. The selected executable should then be available on PATH. If it is not found, repeat the displayed PATH export in the same terminal.

Model IDs download automatically when first used. The optional download command prepares the checkpoint ahead of time. Uncached models require internet access and enough disk space; gated models also require access approval and credentials.

2. Run

Run this command in the same terminal after preparation. For server modes, keep it running and wait for the listening/ready message. If memory is insufficient, select a smaller checkpoint or reduce context/concurrency in advanced settings.

Copy all includes the selected installation, checkpoint download, and displayed run commands, in that order. Run them in the same shell; multi-node commands belong on their respective machines.

mlxcel serve

This installation provides the full CLI. Use mlxcel serve; select a source build to use the standalone server.

mlxcel serve -m mlx-community/Qwen3-4B-4bit --alias qwen3-4b \
  --ctx-size 8192 --n-parallel 4
Command flag help
-m
Selects the model or checkpoint repository.
--alias
Sets the served model name used by API clients.
--ctx-size
Sets the maximum context window for requests.
--n-parallel
Sets the number of parallel server slots.

3. Check the first result

For a server, use a second terminal after it is ready. A text chat request returns JSON with choices[0].message.content; specialized endpoints return their task output. Replace sample file paths with your own inputs where shown. Connection refused: check the server address/port and terminal logs. Model access/download errors: check the model ID, permissions, internet connection, and free disk space.

curl http://127.0.0.1:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3-4b","messages":[{"role":"user","content":"Hello"}]}'

Performance evidence

No benchmark is recorded for this selected checkpoint and hardware combination. Commands and memory estimates use the catalog's model information.

Memory fit is a model-based estimate, separate from measured throughput and successful inference verification.

No measurement is available for this hardware yet. See the family page for related profiles. Family

Prerequisites

  • Install the mlxcel build for your selected hardware and check the selected checkpoint's memory estimate.
  • Allow internet access and enough disk space to download an uncached checkpoint; obtain Hugging Face access approval when the checkpoint requires it.

Recipe options

  • • OpenAI-compatible chat responses return reasoning in reasoning_content and the answer in content. Reasoning display depends on the client.

Family

Qwen 3

Dense

Sibling recipes

pending

Guide

Overview

Qwen3-4B is a dense model for chat and reasoning. This recipe supports mlxcel's thinking controls, tool calling, KV cache quantization, LoRA loading, and memory estimates.

Prerequisites

Start with mlx-community/Qwen3-4B-4bit, or choose mlx-community/Qwen3-4B-8bit if you have enough memory for lower compression. The recipe also lists the original Qwen/Qwen3-4B bf16 checkpoint. On Apple Silicon, mlxcel converts non-quantized bf16 weights to f16 during loading.

Gotchas

Thinking is controlled through chat-template kwargs and --reasoning-budget, so keep it separate from ordinary sampling options. kv_int8 and turbo_kv are mutually exclusive recipe features; select one cache compression strategy at a time and run --estimate-memory before raising --ctx-size.

References