---
language:
- en
license: apache-2.0
tags:
- qwen3.5
- moe
- hermes
- agentic
- tool-calling
- qlora
- unsloth
- carnice
- mlx
- mlx-my-repo
base_model: samuelcardillo/Carnice-MoE-35B-A3B
datasets:
- bespokelabs/Bespoke-Stratos-17k
- AI-MO/NuminaMath-CoT
- kai-os/carnice-glm5-hermes-traces
- open-thoughts/OpenThoughts-Agent-v1-SFT
---

# KnucklesXBT/Carnice-MoE-35B-A3B-mlx-8Bit

The Model [KnucklesXBT/Carnice-MoE-35B-A3B-mlx-8Bit](https://huggingface.co/KnucklesXBT/Carnice-MoE-35B-A3B-mlx-8Bit) was converted to MLX format from [samuelcardillo/Carnice-MoE-35B-A3B](https://huggingface.co/samuelcardillo/Carnice-MoE-35B-A3B) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("KnucklesXBT/Carnice-MoE-35B-A3B-mlx-8Bit")

prompt="hello"

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

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