Downloads · 30 days
30
7% of all-time downloads
Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-8bit
tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-8bit
Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-8bit is a text generation model from tocchitocchi. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
MLX 8bit quantized version of tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2 for Apple Silicon Macs.
All-time downloads
436
Public
Parameters
30.5B
32.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors32.4 GB · 100%
Parameter types
How the weights are stored.
U3230.5B · 100%
Base models
Model card
From the Hugging Face model README
Qwen3-Swallow-30B-A3B-SFT-v0.2 — MLX 8bit
MLX 8bit quantized version 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 | 8bit |
| Model size | ~32 GB |
| Source | tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2 |
Performance (MacBook Pro M4 Max, 128GB)
| Metric | Value |
|---|---|
| Generation speed | 89.7 tokens/s |
| Peak memory usage | 32.5 GB |
Usage
Install
pip install mlx-lm
Text Generation
mlx_lm.generate \
--model tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-8bit \
--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-8bit
OpenAI-Compatible API Server
mlx_lm.server \
--model tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-8bit \
--port 8080
Python API
from mlx_lm import load, generate
model, tokenizer = load("tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-8bit")
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 | Plenty of headroom | ✅ |
| M4 Pro 64GB | Comfortable | ✅ |
| M4 Pro 48GB | Runs fine | ✅ |
| M1/M2/M3 16GB | 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 (this model) | tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-8bit | 32 GB | 89.7 tok/s |
| fp16 | 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)
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_moe
- License
- apache-2.0
- Languages
- ja, en
- Created
- Feb 23, 2026
- Updated
- Feb 24, 2026