---
title: Groot-19B-A3B-OptiQ-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Groot-19B-A3B-OptiQ-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Groot-19B-A3B-OptiQ-4bit.md"
repository: mlx-community/Groot-19B-A3B-OptiQ-4bit
last_updated: 2026-11-05
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5_moe
architectures:
  - Qwen3_5MoeForConditionalGeneration
base_model:
  - GrootTeam/Groot-19B-A3B-261023
base_model_relation: quantized
parameters: 3.8B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 30
stars: 0
tags:
  - mlx
  - quantized
  - mixed-precision
  - 4bit
  - 8bit
  - moe
  - optiq
  - apple-silicon
  - groot
---

# Groot-19B-A3B-OptiQ-4bit

> Groot-19B-A3B-OptiQ-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Groot-19B-A3B-OptiQ-4bit

mlx-community/Groot-19B-A3B-OptiQ-4bit 是 ModelScope 魔搭社区上的 3.8B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 GrootTeam/Groot-19B-A3B-261023 构建。

- **Repository**: mlx-community/Groot-19B-A3B-OptiQ-4bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 3.8B
- **Base model**: GrootTeam/Groot-19B-A3B-261023
- **Tags**: mlx, quantized, mixed-precision, 4bit, 8bit, moe, optiq, apple-silicon, groot
- **Downloads**: 30
- **Stars**: 0
- **Last updated**: 2026-11-05

Source: https://www.modelscope.cn/models/mlx-community/Groot-19B-A3B-OptiQ-4bit

---

# mlx-community/Groot-19B-A3B-OptiQ-4bit

> **Built with [mlx-optiq](https://mlx-optiq.com)**, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon. [All OptiQ models](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/)

A 4-bit mixed-precision MLX quant of [GrootTeam/Groot-19B-A3B-261023](https://huggingface.co/GrootTeam/Groot-19B-A3B-261023), a reasoning model post-trained from Qwen3.6-35B-A3B. It has 128 routed experts per layer and activates 8 per token. Text, tool calling and image input all work.

| | |
|---|---|
| On disk | 13.5 GB, including the 0.9 GB vision tower and 0.3 GB MTP head (source BF16 38.9 GB) |
| Parameters | 19B total, about 3B active per token |
| Precision | 118 tensors at 4-bit, 394 at 8-bit, vision tower at bf16 |
| Capability Score | 78.37 |

## Benchmarks

Six-metric Capability Score, the mean of MMLU, GSM8K, IFEval, BFCL, HumanEval and HashHop, measured on a 24 GB M4 with mlx-optiq 0.8.0. The comparison column is from the card of [Qwen3.6-35B-A3B-OptiQ-4bit](https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit), the model Groot was post-trained from, measured with an earlier mlx-optiq version.

| Metric | This model | Qwen3.6-35B-A3B-OptiQ-4bit | Δ |
|---|---:|---:|---:|
| MMLU (5-shot, 1000 samples) | **70.6%** | 83.7% | -13.1 |
| GSM8K (1000 samples) | **94.4%** | 87.9% | +6.5 |
| IFEval (full set, strict) | **77.1%** | 72.6% | +4.5 |
| BFCL-V3 simple (200 calls) | **92.5%** | 92.5% | 0.0 |
| HumanEval (164 problems, pass@1) | **89.6%** | 91.5% | -1.9 |
| HashHop (long-context retrieval) | **46.0%** | 52.0% | -6.0 |
| **Capability Score** (mean of 6) | **78.37** | 80.03 | **-1.66** |

At 13.5 GB against 23.0 GB, it scores 1.66 lower than the 35B quant. It also scores 1.80 above [Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B](https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B) (76.57), the pruned quant of about the same size.

## How it was made

The per-layer bit allocation is reused from [Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B](https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B), which has the same 128-expert layout. All 512 tensors matched. No sensitivity sweep was run on this checkpoint. The KV config was measured on this model.

## Use it

```bash
pip install mlx-optiq
optiq serve --model mlx-community/Groot-19B-A3B-OptiQ-4bit
```

```python
from mlx_lm import load, generate
model, tok = load("mlx-community/Groot-19B-A3B-OptiQ-4bit")
print(generate(model, tok, prompt="Hello", max_tokens=64))
```