Instructions to use tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 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("tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16")

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 tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16"

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": "tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 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 "tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16"

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 tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16"

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 "tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16" \
  --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"

Qwen3-Swallow-30B-A3B-SFT-v0.2 — MLX fp16

MLX fp16 (unquantized) conversion of tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2 for Apple Silicon Macs.

Model Details

Original model: tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2
Architecture: Mixture of Experts (MoE) — 30B total parameters, 3B active parameters
Training: Japanese Continued Pre-Training + Supervised Fine-Tuning by Tokyo Institute of Technology Swallow Project
License: Apache 2.0

Conversion Details

Item	Value
Conversion tool	mlx-lm
Quantization	None (fp16)
Model size	~61 GB
Source	`tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2`

Performance (MacBook Pro M4 Max, 128GB)

Metric	Value
Generation speed	60.9 tokens/s
Peak memory usage	61.1 GB

No quantization is applied, providing the highest output quality. Recommended for environments with ample memory (96 GB or more).

Usage

Install

pip install mlx-lm

Text Generation

mlx_lm.generate \
  --model tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 \
  --prompt "生成AIについて、10歳向けの説明をして" \
  --max-tokens 500

Chat

mlx_lm.chat --model tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16

OpenAI-Compatible API Server

mlx_lm.server \
  --model tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 \
  --port 8080

Python API

from mlx_lm import load, generate

model, tokenizer = load("tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16")
messages = [{"role": "user", "content": "日本の四季の魅力を説明して"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
print(generate(model, tokenizer, prompt=prompt, max_tokens=500))

Recommended Hardware

Machine	Memory	Status
M4 Max 128GB	Comfortable	✅
M4 Pro/Max 96GB	Runs fine	✅
M4 Pro 64GB	Tight	⚠️
48 GB or less	Not enough	❌

Other Variants

Precision	Repository	Size	Speed
4bit	tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-4bit	17 GB	120.6 tok/s
8bit	tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-8bit	32 GB	89.7 tok/s
fp16 (this model)	tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16	61 GB	60.9 tok/s

Compatible Tools

mlx-lm (CLI / Python / API server)
LM Studio (GUI app)
Pico AI Server (App Store)

Downloads last month: 30

Safetensors

Model size

31B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16

Base model

Qwen/Qwen3-30B-A3B-Base

Finetuned

tokyotech-llm/Qwen3-Swallow-30B-A3B-CPT-v0.2

Finetuned

tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2

Finetuned

(2)

this model