---
license: apache-2.0
tags:
- yi
- moe
- TensorBlock
- GGUF
base_model: cloudyu/Mixtral_34Bx2_MoE_60B
model-index:
- name: Mixtral_34Bx2_MoE_60B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 45.38
      name: strict accuracy
    source:
      url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 41.21
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 6.57
      name: exact match
    source:
      url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 11.74
      name: acc_norm
    source:
      url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 17.78
      name: acc_norm
    source:
      url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 41.85
      name: accuracy
    source:
      url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
      name: Open LLM Leaderboard
---

<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>

## cloudyu/Mixtral_34Bx2_MoE_60B - GGUF

This repo contains GGUF format model files for [cloudyu/Mixtral_34Bx2_MoE_60B](https://huggingface.co./cloudyu/Mixtral_34Bx2_MoE_60B).

The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).

<div style="text-align: left; margin: 20px 0;">
    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
        Run them on the TensorBlock client using your local machine ↗
    </a>
</div>

## Prompt template

```

```

## Model file specification

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Mixtral_34Bx2_MoE_60B-Q2_K.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q2_K.gguf) | Q2_K | 22.394 GB | smallest, significant quality loss - not recommended for most purposes |
| [Mixtral_34Bx2_MoE_60B-Q3_K_S.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q3_K_S.gguf) | Q3_K_S | 26.318 GB | very small, high quality loss |
| [Mixtral_34Bx2_MoE_60B-Q3_K_M.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q3_K_M.gguf) | Q3_K_M | 29.237 GB | very small, high quality loss |
| [Mixtral_34Bx2_MoE_60B-Q3_K_L.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q3_K_L.gguf) | Q3_K_L | 31.768 GB | small, substantial quality loss |
| [Mixtral_34Bx2_MoE_60B-Q4_0.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q4_0.gguf) | Q4_0 | 34.334 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Mixtral_34Bx2_MoE_60B-Q4_K_S.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q4_K_S.gguf) | Q4_K_S | 34.594 GB | small, greater quality loss |
| [Mixtral_34Bx2_MoE_60B-Q4_K_M.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q4_K_M.gguf) | Q4_K_M | 36.661 GB | medium, balanced quality - recommended |
| [Mixtral_34Bx2_MoE_60B-Q5_0.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q5_0.gguf) | Q5_0 | 41.878 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [Mixtral_34Bx2_MoE_60B-Q5_K_S.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q5_K_S.gguf) | Q5_K_S | 41.878 GB | large, low quality loss - recommended |
| [Mixtral_34Bx2_MoE_60B-Q5_K_M.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q5_K_M.gguf) | Q5_K_M | 43.077 GB | large, very low quality loss - recommended |
| [Mixtral_34Bx2_MoE_60B-Q6_K.gguf](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q6_K.gguf) | Q6_K | 49.893 GB | very large, extremely low quality loss |
| [Mixtral_34Bx2_MoE_60B-Q8_0](https://huggingface.co./tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q8_0) | Q8_0 | 0.959 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/Mixtral_34Bx2_MoE_60B-GGUF --include "Mixtral_34Bx2_MoE_60B-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/Mixtral_34Bx2_MoE_60B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```