---
title: ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit.md"
repository: mlx-community/ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit
last_updated: 2026-03-27
license: llama3.3
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - DataPilot/ArrowCanaria-Llama-8B-RL-v0.1
base_model_relation: quantized
parameters: 2.3B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ja
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 9
stars: 0
tags:
  - mlx
---

# ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit

> ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit - mlx-community 在 ModelScope 开源的模型。This model was converted to MLX format from DataPilot/ArrowCanaria-Llama-8B-RL-v0.1 using mlx-lm version 0.31.0. Refer to the original model card for more details on the model.

mlx-community/ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit 是 ModelScope 魔搭社区上的 2.3B 参数text-generation模型，采用 llama3.3 许可，基于 DataPilot/ArrowCanaria-Llama-8B-RL-v0.1 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit
- **License**: llama3.3
- **Tasks**: text-generation
- **Parameters**: 2.3B
- **Base model**: DataPilot/ArrowCanaria-Llama-8B-RL-v0.1
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 9
- **Stars**: 0
- **Last updated**: 2026-03-27

Source: https://www.modelscope.cn/models/mlx-community/ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit

---

This model was converted to MLX format from [`DataPilot/ArrowCanaria-Llama-8B-RL-v0.1`](https://huggingface.co/DataPilot/ArrowCanaria-Llama-8B-RL-v0.1) using mlx-lm version **0.31.0**.
Refer to the [original model card](https://huggingface.co/DataPilot/ArrowCanaria-Llama-8B-RL-v0.1) for more details on the model.

Inference: M3 Ultra - LM Studio MLX v1.4
-----
8bit 75.22tok/s
おはよう
arrowcanaria-llama-8b-rl-v0.1-mlx@8bit

おはようございます！今日も一日、元気に過ごしましょう。何か心配事や話したいことがあれば、お手伝いさせていただきます。