---
license: apache-2.0
base_model: allura-org/Q3-8B-Kintsugi
library_name: mlx
tags:
- mergekit
- axolotl
- unsloth
- roleplay
- conversational
- mlx
datasets:
- PygmalionAI/PIPPA
- Alfitaria/nemotron-ultra-reasoning-synthkink
- PocketDoc/Dans-Prosemaxx-Gutenberg
- FreedomIntelligence/Medical-R1-Distill-Data
- cognitivecomputations/SystemChat-2.0
- allenai/tulu-3-sft-personas-instruction-following
- kalomaze/Opus_Instruct_25k
- simplescaling/s1K-claude-3-7-sonnet
- ai2-adapt-dev/flan_v2_converted
- grimulkan/theory-of-mind
- grimulkan/physical-reasoning
- nvidia/HelpSteer3
- nbeerbower/gutenberg2-dpo
- nbeerbower/gutenberg-moderne-dpo
- nbeerbower/Purpura-DPO
- antiven0m/physical-reasoning-dpo
- allenai/tulu-3-IF-augmented-on-policy-70b
- NobodyExistsOnTheInternet/system-message-DPO
pipeline_tag: text-generation
---

# soundTeam/Q3-8B-Kintsugi_mlx-4bpw

This model [soundTeam/Q3-8B-Kintsugi_mlx-4bpw](https://huggingface.co/soundTeam/Q3-8B-Kintsugi_mlx-4bpw) was
converted to MLX format from [allura-org/Q3-8B-Kintsugi](https://huggingface.co/allura-org/Q3-8B-Kintsugi)
using mlx-lm version **0.25.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("soundTeam/Q3-8B-Kintsugi_mlx-4bpw")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```