---
pipeline_tag: text-generation
inference: false
license: apache-2.0
library_name: transformers
tags:
- TensorBlock
- GGUF
base_model: ibm-research/PowerMoE-3b
model-index:
- name: ibm/PowerMoE-3b
  results:
  - task:
      type: text-generation
    dataset:
      name: ARC
      type: lm-eval-harness
    metrics:
    - type: accuracy-norm
      value: 58.1
      name: accuracy-norm
      verified: false
    - type: accuracy
      value: 65.0
      name: accuracy
      verified: false
    - type: accuracy-norm
      value: 71.5
      name: accuracy-norm
      verified: false
    - type: accuracy-norm
      value: 41.0
      name: accuracy-norm
      verified: false
    - type: accuracy-norm
      value: 79.1
      name: accuracy-norm
      verified: false
    - type: accuracy-norm
      value: 65.0
      name: accuracy-norm
      verified: false
    - type: accuracy
      value: 42.8
      name: accuracy
      verified: false
    - type: accuracy
      value: 25.9
      name: accuracy
      verified: false
    - type: accuracy
      value: 14.8
      name: accuracy
      verified: false
  - task:
      type: text-generation
    dataset:
      name: humaneval
      type: bigcode-eval
    metrics:
    - type: pass@1
      value: 20.1
      name: pass@1
      verified: false
    - type: pass@1
      value: 32.4
      name: pass@1
      verified: false
---

<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;">
            Feedback and support: TensorBlock's  <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
        </p>
    </div>
</div>

## ibm-research/PowerMoE-3b - GGUF

This repo contains GGUF format model files for [ibm-research/PowerMoE-3b](https://huggingface.co/ibm-research/PowerMoE-3b).

The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5165](https://github.com/ggml-org/llama.cpp/commit/1d735c0b4fa0551c51c2f4ac888dd9a01f447985).

## Our projects
<table border="1" cellspacing="0" cellpadding="10">
<tr>
  <th style="font-size: 25px;">Awesome MCP Servers</th>
  <th style="font-size: 25px;">TensorBlock Studio</th>
</tr>
  <tr>
    <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
    <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
  </tr>
  <tr>
    <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
    <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
  </tr>
<tr>
  <th>
    <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
      display: inline-block;
      padding: 8px 16px;
      background-color: #FF7F50;
      color: white;
      text-decoration: none;
      border-radius: 6px;
      font-weight: bold;
      font-family: sans-serif;
    ">👀 See what we built 👀</a>
  </th>
  <th>
    <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
      display: inline-block;
      padding: 8px 16px;
      background-color: #FF7F50;
      color: white;
      text-decoration: none;
      border-radius: 6px;
      font-weight: bold;
      font-family: sans-serif;
    ">👀 See what we built 👀</a>
  </th>
</tr>
</table>

## Prompt template

```
Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
```

## Model file specification

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [PowerMoE-3b-Q2_K.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q2_K.gguf) | Q2_K | 1.266 GB | smallest, significant quality loss - not recommended for most purposes |
| [PowerMoE-3b-Q3_K_S.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q3_K_S.gguf) | Q3_K_S | 1.488 GB | very small, high quality loss |
| [PowerMoE-3b-Q3_K_M.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q3_K_M.gguf) | Q3_K_M | 1.644 GB | very small, high quality loss |
| [PowerMoE-3b-Q3_K_L.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q3_K_L.gguf) | Q3_K_L | 1.774 GB | small, substantial quality loss |
| [PowerMoE-3b-Q4_0.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q4_0.gguf) | Q4_0 | 1.926 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [PowerMoE-3b-Q4_K_S.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q4_K_S.gguf) | Q4_K_S | 1.942 GB | small, greater quality loss |
| [PowerMoE-3b-Q4_K_M.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q4_K_M.gguf) | Q4_K_M | 2.059 GB | medium, balanced quality - recommended |
| [PowerMoE-3b-Q5_0.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q5_0.gguf) | Q5_0 | 2.338 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [PowerMoE-3b-Q5_K_S.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q5_K_S.gguf) | Q5_K_S | 2.338 GB | large, low quality loss - recommended |
| [PowerMoE-3b-Q5_K_M.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q5_K_M.gguf) | Q5_K_M | 2.407 GB | large, very low quality loss - recommended |
| [PowerMoE-3b-Q6_K.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q6_K.gguf) | Q6_K | 2.776 GB | very large, extremely low quality loss |
| [PowerMoE-3b-Q8_0.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q8_0.gguf) | Q8_0 | 3.593 GB | very large, extremely low quality loss - not recommended |


## Downloading instruction

### Command line

Firstly, install Huggingface Client

```shell
pip install -U "huggingface_hub[cli]"
```

Then, downoad the individual model file the a local directory

```shell
huggingface-cli download tensorblock/ibm-research_PowerMoE-3b-GGUF --include "PowerMoE-3b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
```

If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:

```shell
huggingface-cli download tensorblock/ibm-research_PowerMoE-3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```