# Can the Radeon RX 7800 XT run Crowd-v1?

> Yes. The Radeon RX 7800 XT runs Crowd-v1 fully in VRAM at FP16 / BF16 (about 2.8 GB of 16 GB), at roughly 172 tokens/s.

Radeon RX 7800 XT: 16 GB (16 GB usable), 624 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 1.18 | fits | 1044 |
| Q3_K_M | Noticeable loss | 1.34 | fits | 702 |
| Q4_K_M | Small loss | 1.45 | fits | 566 |
| Q5_K_M | Near-lossless | 1.56 | fits | 483 |
| Q6_K | Near-lossless | 1.67 | fits | 417 |
| Q8_0 | Lossless | 1.9 | fits | 323 |
| F16 (pick) | Lossless | 2.82 | fits | 172 |

## Chat models that fit comfortably

- [google/gemma-3-1b-it](https://selfhost.directory/models/google/gemma-3-1b-it/on/rx-7800-xt): Q8_0 ≈1.75 GB, est. 323 tok/s
- [Qwen/Qwen3-0.6B](https://selfhost.directory/models/qwen/qwen3-0.6b/on/rx-7800-xt): Q8_0 ≈2.01 GB, est. 430 tok/s
- [meta-llama/Llama-3.2-1B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-1b-instruct/on/rx-7800-xt): Q8_0 ≈2.04 GB, est. 261 tok/s
- [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://selfhost.directory/models/tinyllama/tinyllama-1.1b-chat-v1.0/on/rx-7800-xt): Q8_0 ≈1.68 GB, est. 294 tok/s
- [LiquidAI/LFM3-1.7B](https://selfhost.directory/models/liquidai/lfm3-1.7b/on/rx-7800-xt): Q8_0 ≈2.69 GB, est. 187 tok/s
- [Qwen/Qwen2.5-1.5B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-1.5b-instruct/on/rx-7800-xt): Q8_0 ≈2.57 GB, est. 209 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/vxtzq/crowd-v1/on/rtx-4060): F16, est. 75 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/vxtzq/crowd-v1/on/apple-m4-16gb): F16, est. 33 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/vxtzq/crowd-v1/on/rx-6700-xt): F16, est. 106 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/vxtzq/crowd-v1/on/rtx-3060): F16, est. 99 tok/s
- [Arc B580](https://selfhost.directory/models/vxtzq/crowd-v1/on/arc-b580): F16, est. 125 tok/s
- [Tesla T4](https://selfhost.directory/models/vxtzq/crowd-v1/on/tesla-t4): F16, est. 88 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/vxtzq/crowd-v1/on/arc-a770): F16, est. 154 tok/s
- [Radeon RX 9070 XT](https://selfhost.directory/models/vxtzq/crowd-v1/on/rx-9070-xt): F16, est. 176 tok/s

---
Model: https://selfhost.directory/models/vxtzq/crowd-v1. GPU: https://selfhost.directory/models/gpus/rx-7800-xt. Source: https://selfhost.directory/models/vxtzq/crowd-v1/on/rx-7800-xt