---
title: Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit.md"
repository: mlx-community/Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit
last_updated: 2026-03-28
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - nri-ai/Qwen3-14B-Ja-Fin-Thinking
base_model_relation: quantized
parameters: 2.3B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ja
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 12
stars: 0
tags:
  - mlx
---

# Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit

> Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit - mlx-community 在 ModelScope 开源的模型。This model was converted to MLX format from nri-ai/Qwen3-14B-Ja-Fin-Thinking using mlx-lm version 0.31.0. Refer to the original model card for more details on the model.

mlx-community/Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit 是 ModelScope 魔搭社区上的 2.3B 参数text-generation模型，采用 apache-2.0 许可，基于 nri-ai/Qwen3-14B-Ja-Fin-Thinking 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 2.3B
- **Base model**: nri-ai/Qwen3-14B-Ja-Fin-Thinking
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 12
- **Stars**: 0
- **Last updated**: 2026-03-28

Source: https://www.modelscope.cn/models/mlx-community/Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit

---

This model was converted to MLX format from [`nri-ai/Qwen3-14B-Ja-Fin-Thinking`](https://huggingface.co/nri-ai/Qwen3-14B-Ja-Fin-Thinking) using mlx-lm version **0.31.0**.
Refer to the [original model card](https://huggingface.co/nri-ai/Qwen3-14B-Ja-Fin-Thinking) for more details on the model.

Inference: M3 Ultra - LM Studio MLX v1.4
-----
4bit 45.32 tok/s
分散投資のメリットとデメリットを説明してください。
qwen3-14b-ja-fin-thinking-mlx@4bit

分散投資（Diversification）とは
複数の銘柄・資産クラス・地域・業種などに投資先を分け、1 つのリスク要因がポートフォリオ全体に与える影響を小さくする手法です。

1. メリット（利点） … continue