# Can the RTX A6000 run Darwin-27B-RSI?

> Yes. The RTX A6000 runs Darwin-27B-RSI fully in VRAM at Q8_0 (about 31 GB of 48 GB), at roughly 15 tokens/s.

RTX A6000: 48 GB (48 GB usable), 768 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 12.85 | fits | 48 |
| Q3_K_M | Noticeable loss | 15.37 | fits | 32 |
| Q4_K_M | Small loss | 18.94 | fits | 26 |
| Q5_K_M | Near-lossless | 22.72 | fits | 22 |
| Q6_K | Near-lossless | 25.6 | fits | 19 |
| Q8_0 (pick) | Lossless | 30.54 | fits | 15 |
| F16 | Lossless | 55.12 | offload | 3.1 |

## Run it

Q8_0 straight from Hugging Face (ollama):

```bash
ollama run hf.co/bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF:Q8_0
```

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

```bash
llama-server -hf bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF:Q8_0
```

Download with the lms CLI (lmstudio):

```bash
lms get bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF@Q8_0
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve FINAL-Bench/Darwin-27B-RSI
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: FINAL-Bench/Darwin-27B-RSI
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Serve an OpenAI-compatible API (sglang):

```bash
sglang serve FINAL-Bench/Darwin-27B-RSI --host 0.0.0.0 --port 30000
```

Docker Compose (NVIDIA) (sglang):

```yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve FINAL-Bench/Darwin-27B-RSI --host 0.0.0.0 --port 30000
    ports:
      - "30000:30000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Chat with the pipeline API (transformers):

```python
from transformers import pipeline

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-27B-RSI", 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

- [openai/gpt-oss-20b](https://selfhost.directory/models/openai/gpt-oss-20b/on/rtx-a6000): Q8_0 ≈12.72 GB, est. 95 tok/s
- [zai-org/GLM-4.7-Flash](https://selfhost.directory/models/zai-org/glm-4.7-flash/on/rtx-a6000): Q8_0 ≈38.98 GB, est. 86 tok/s
- [ornith-ai/Ornith-1.5-35B-A3B](https://selfhost.directory/models/ornith-ai/ornith-1.5-35b-a3b/on/rtx-a6000): Q8_0 ≈38.11 GB, est. 133 tok/s
- [Qwen/Qwen3-32B](https://selfhost.directory/models/qwen/qwen3-32b/on/rtx-a6000): Q8_0 ≈36.55 GB, est. 12 tok/s
- [Qwen/Qwen3-30B-A3B](https://selfhost.directory/models/qwen/qwen3-30b-a3b/on/rtx-a6000): Q8_0 ≈33.01 GB, est. 133 tok/s
- [LiquidAI/LFM2.5-24B-A2B](https://selfhost.directory/models/liquidai/lfm2.5-24b-a2b/on/rtx-a6000): Q8_0 ≈26.06 GB, est. 199 tok/s

## Other GPUs that run it

- [Tesla T4](https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/tesla-t4): Q3_K_M, est. 13 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/arc-a770): Q3_K_M, est. 23 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/rx-7800-xt): Q3_K_M, est. 26 tok/s
- [Tesla P40](https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/tesla-p40): Q5_K_M, est. 10 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/rx-7900-xtx): Q5_K_M, est. 28 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/instinct-mi50): Q6_K, est. 25 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/rtx-5090): Q6_K, est. 44 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/apple-m4-pro-48gb): Q8_0, est. 5.3 tok/s

---
Model: https://selfhost.directory/models/final-bench/darwin-27b-rsi. GPU: https://selfhost.directory/models/gpus/rtx-a6000. Source: https://selfhost.directory/models/final-bench/darwin-27b-rsi/on/rtx-a6000