Downloads · 30 days
29
8% of all-time downloads
Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16
tocchitocchi/Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16
Qwen3-Swallow-30B-A3B-SFT-v0.2-MLX-fp16 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 fp16 (unquantized) conversion of tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2 for Apple Silicon Macs.
All-time downloads
385
Public
Parameters
30.5B
61.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors61.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- mlx
- License
- apache-2.0
- Model type
- qwen3_moe
- Access
- Public
- Created
- Feb 23, 2026
- Updated
- Feb 24, 2026
- SHA
- 90f62734
Base models
Model card
From the Hugging Face model README
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)
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_moe
- License
- apache-2.0
- Languages
- ja, en
- Created
- Feb 23, 2026
- Updated
- Feb 24, 2026