# Can the Radeon RX 6700 XT run LFM3-1.7B-Base?

> Yes. The Radeon RX 6700 XT runs LFM3-1.7B-Base fully in VRAM at FP16 / BF16 (about 4.3 GB of 12 GB), at roughly 61 tokens/s.

Radeon RX 6700 XT: 12 GB (12 GB usable), 384 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 1.62 | fits | 372 |
| Q3_K_M | Noticeable loss | 1.77 | fits | 250 |
| Q4_K_M | Small loss | 1.95 | fits | 202 |
| Q5_K_M | Near-lossless | 2.11 | fits | 172 |
| Q6_K | Near-lossless | 2.28 | fits | 148 |
| Q8_0 | Lossless | 2.69 | fits | 115 |
| F16 (pick) | Lossless | 4.27 | fits | 61 |

## Run it

From the Ollama library (ollama):

```bash
ollama run lfm3:1.7b
```

F16 straight from Hugging Face (ollama):

```bash
ollama run hf.co/mradermacher/LFM3-1.7B-Base-GGUF:F16
```

Docker with ROCm (AMD) (ollama):

```bash
docker run -d --name ollama --device /dev/kfd --device /dev/dri \
  -e HSA_OVERRIDE_GFX_VERSION=10.3.0 \
  -v ollama:/root/.ollama -p 11434:11434 ollama/ollama:rocm
docker exec -it ollama ollama run lfm3:1.7b
```

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

```bash
llama-server -hf mradermacher/LFM3-1.7B-Base-GGUF:F16
```

Docker with ROCm (AMD) (llama.cpp):

```bash
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
  -e HSA_OVERRIDE_GFX_VERSION=10.3.0 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-rocm \
  -hf mradermacher/LFM3-1.7B-Base-GGUF:F16 --host 0.0.0.0 --port 8080 -ngl 99
```

Chat with the pipeline API (transformers):

```python
from transformers import pipeline

pipe = pipeline("text-generation", model="LiquidAI/LFM3-1.7B-Base", 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

- [LiquidAI/LFM3-1.7B](https://selfhost.directory/models/liquidai/lfm3-1.7b/on/rx-6700-xt): Q8_0 ≈2.69 GB, est. 115 tok/s
- [Qwen/Qwen2.5-1.5B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-1.5b-instruct/on/rx-6700-xt): Q8_0 ≈2.57 GB, est. 129 tok/s
- [Qwen/Qwen3-1.7B](https://selfhost.directory/models/qwen/qwen3-1.7b/on/rx-6700-xt): Q8_0 ≈3.18 GB, est. 98 tok/s
- [meta-llama/Llama-3.2-1B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-1b-instruct/on/rx-6700-xt): Q8_0 ≈2.04 GB, est. 161 tok/s
- [google/gemma-3-1b-it](https://selfhost.directory/models/google/gemma-3-1b-it/on/rx-6700-xt): Q8_0 ≈1.75 GB, est. 199 tok/s
- [openbmb/MiniCPM5-2B](https://selfhost.directory/models/openbmb/minicpm5-2b/on/rx-6700-xt): Q8_0 ≈3.46 GB, est. 79 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/rtx-4060): F16, est. 43 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/apple-m4-16gb): F16, est. 19 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/rtx-3060): F16, est. 57 tok/s
- [Arc B580](https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/arc-b580): F16, est. 73 tok/s
- [Tesla T4](https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/tesla-t4): F16, est. 51 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/arc-a770): F16, est. 89 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/rx-7800-xt): F16, est. 99 tok/s
- [Tesla P40](https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/tesla-p40): F16, est. 55 tok/s

---
Model: https://selfhost.directory/models/liquidai/lfm3-1.7b-base. GPU: https://selfhost.directory/models/gpus/rx-6700-xt. Source: https://selfhost.directory/models/liquidai/lfm3-1.7b-base/on/rx-6700-xt