---
title: Tiny-Pickle-v3-Coder-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Tiny-Pickle-v3-Coder-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Tiny-Pickle-v3-Coder-4bit.md"
repository: mlx-community/Tiny-Pickle-v3-Coder-4bit
last_updated: 2026-08-06
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_moe
architectures:
  - Qwen3MoeForCausalLM
base_model:
  - vsan/tiny-pickle-v3-coder
base_model_relation: quantized
parameters: 4.8B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 23
stars: 0
tags:
  - mlx
  - qwen3-coder
  - coding
  - software-engineering
  - quantized
  - 4bit
  - apple-silicon
  - moe
  - tiny-pickle
---

# Tiny-Pickle-v3-Coder-4bit

> Tiny-Pickle-v3-Coder-4bit - mlx-community 在 ModelScope 开源的模型。Tiny Pickle v3 Coder — MLX 4-bit

mlx-community/Tiny-Pickle-v3-Coder-4bit 是 ModelScope 魔搭社区上的 4.8B 参数text-generation模型，采用 apache-2.0 许可，基于 vsan/tiny-pickle-v3-coder 构建。

- **Repository**: mlx-community/Tiny-Pickle-v3-Coder-4bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 4.8B
- **Base model**: vsan/tiny-pickle-v3-coder
- **Tags**: mlx, qwen3-coder, coding, software-engineering, quantized, 4bit, apple-silicon, moe, tiny-pickle
- **Downloads**: 23
- **Stars**: 0
- **Last updated**: 2026-08-06

Source: https://www.modelscope.cn/models/mlx-community/Tiny-Pickle-v3-Coder-4bit

---

# Tiny Pickle v3 Coder — MLX 4-bit

Tiny Pickle v3 Coder is a coding-focused adaptation of
`Qwen/Qwen3-Coder-30B-A3B-Instruct`, converted to MLX and quantized for
Apple Silicon.

## Model lineage

- Base model: `Qwen/Qwen3-Coder-30B-A3B-Instruct`
- LoRA adapter: `vsan/tiny-pickle-v3-coder-LoRA`
- Merged Safetensors: `vsan/tiny-pickle-v3-coder`
- Quantization: MLX affine 4-bit
- Group size: 64
- Converted directory size:  16G

## Installation

```bash
pip install -U mlx-lm
```

## Interactive chat

```bash
mlx_lm.chat --model mlx-community/Tiny-Pickle-v3-Coder-4bit
```

## Command-line generation

```bash
mlx_lm.generate \
  --model mlx-community/Tiny-Pickle-v3-Coder-4bit \
  --prompt "Write a tested Python implementation of an LRU cache." \
  --max-tokens 800
```

## Intended use

Code generation, debugging, code review, implementation planning, test
generation, and local software-engineering assistance on Apple Silicon.

## Quantization

This release uses MLX 4-bit affine quantization with group size 64.
Quantization reduces storage and unified-memory requirements but may alter
outputs or reduce quality relative to the merged BF16 model.

## Limitations

Tiny Pickle v3 Coder is experimental and has not yet been independently
demonstrated to outperform its base model. Generated code may be incorrect,
insecure, incomplete, or non-functional and must be reviewed and tested.

## Related repositories

- LoRA: https://huggingface.co/vsan/tiny-pickle-v3-coder-LoRA
- Merged Safetensors: https://huggingface.co/vsan/tiny-pickle-v3-coder
- GGUF: https://huggingface.co/vsan/tiny-pickle-v3-coder-GGUF

## Local Performance

The following result is a single local inference measurement, not a standardized benchmark.

| Property | Result |
|---|---:|
| Hardware | Apple M1 Max |
| Unified memory | 64 GB |
| Model format | MLX 4-bit affine |
| Quantization group size | 64 |
| Prompt length | 118 tokens |
| Prompt processing speed | 119.328 tokens/s |
| Generated length | 748 tokens |
| Generation speed | 63.481 tokens/s |
| Peak unified memory | 17.393 GB |

### Test prompt

> You are reviewing a Python async web crawler. Implement a complete, production-quality crawler that uses asyncio and aiohttp; limits global concurrency to 20; limits each domain to 2 concurrent requests; respects robots.txt; retries HTTP 429 and 5xx responses with exponential backoff and jitter; avoids duplicate URLs; normalizes relative links; restricts crawling to the starting domain; supports cancellation; records failures without stopping the crawl; and includes pytest tests using mocked HTTP responses. Return one self-contained Python module followed by the tests.

Results can vary with the macOS version, MLX-LM version, background processes, context length, sampling configuration, and thermal state.