# Can the Apple M4 (16 GB) run Raon-1-nano?

> Yes. The Apple M4 (16 GB) runs Raon-1-nano fully in unified memory at FP16 / BF16 (about 9.6 GB of 11 GB), at roughly 9.3 tokens/s.

Apple M4 (16 GB): 16 GB (10.7 GB usable), 120 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 4.63 | fits | 57 |
| Q3_K_M | Noticeable loss | 5.19 | fits | 38 |
| Q4_K_M | Small loss | 5.54 | fits | 31 |
| Q5_K_M | Near-lossless | 6.01 | fits | 26 |
| Q6_K | Near-lossless | 6.08 | fits | 23 |
| Q8_0 | Lossless | 6.82 | fits | 18 |
| F16 (pick) | Lossless | 9.63 | fits | 9.3 |

## Run it

Apple Silicon with mlx-lm (mlx):

```bash
pip install mlx-lm
mlx_lm.generate --model KRAFTON/Raon-1-nano-mlx --prompt "Hello"
```

OpenAI-compatible server (mlx):

```bash
mlx_lm.server --model KRAFTON/Raon-1-nano-mlx --port 8080
```

F16 straight from Hugging Face (ollama):

```bash
ollama run hf.co/KRAFTON/Raon-1-nano-gguf:F16
```

OpenAI-compatible server with a web UI (llama.cpp):

```bash
llama-server -hf KRAFTON/Raon-1-nano-gguf:F16
```

Download with the lms CLI (lmstudio):

```bash
lms get KRAFTON/Raon-1-nano-gguf@F16
```

Chat with the pipeline API (transformers):

```python
from transformers import pipeline

pipe = pipeline("text-generation", model="KRAFTON/Raon-1-nano", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])
```


## Chat models that fit comfortably

- [meta-llama/Llama-3.2-3B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-3b-instruct/on/apple-m4-16gb): Q8_0 ≈4.73 GB, est. 19 tok/s
- [Qwen/Qwen3-4B](https://selfhost.directory/models/qwen/qwen3-4b/on/apple-m4-16gb): Q8_0 ≈5.82 GB, est. 15 tok/s
- [Qwen/Qwen2.5-3B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-3b-instruct/on/apple-m4-16gb): Q8_0 ≈4.32 GB, est. 20 tok/s
- [microsoft/Phi-4-mini-instruct](https://selfhost.directory/models/microsoft/phi-4-mini-instruct/on/apple-m4-16gb): Q8_0 ≈5.49 GB, est. 16 tok/s
- [ibm-granite/granite-4.2-3b](https://selfhost.directory/models/ibm-granite/granite-4.2-3b/on/apple-m4-16gb): Q8_0 ≈4.94 GB, est. 17 tok/s
- [Qwen/Qwen3-4B-Instruct-2507](https://selfhost.directory/models/qwen/qwen3-4b-instruct-2507/on/apple-m4-16gb): Q8_0 ≈5.82 GB, est. 15 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/krafton/raon-1-nano/on/rtx-4060): Q8_0, est. 40 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/krafton/raon-1-nano/on/rx-6700-xt): F16, est. 30 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/krafton/raon-1-nano/on/rtx-3060): F16, est. 28 tok/s
- [Arc B580](https://selfhost.directory/models/krafton/raon-1-nano/on/arc-b580): F16, est. 36 tok/s
- [Tesla T4](https://selfhost.directory/models/krafton/raon-1-nano/on/tesla-t4): F16, est. 25 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/krafton/raon-1-nano/on/arc-a770): F16, est. 44 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/krafton/raon-1-nano/on/rx-7800-xt): F16, est. 49 tok/s
- [Tesla P40](https://selfhost.directory/models/krafton/raon-1-nano/on/tesla-p40): F16, est. 27 tok/s

---
Model: https://selfhost.directory/models/krafton/raon-1-nano. GPU: https://selfhost.directory/models/gpus/apple-m4-16gb. Source: https://selfhost.directory/models/krafton/raon-1-nano/on/apple-m4-16gb