# AMD Radeon RX 7900 XTX for local LLMs

> 24GB at 960 GB/s with solid ROCm and Vulkan support, though used prices now rival a 3090.

The RX 7900 XTX has 24GB of GDDR6 and 960 GB/s of memory bandwidth, which decides how big a model fits and how fast it generates text. It comfortably runs models up to about 35B parameters: the largest in our catalog is Qwen3.6 35B-A3B at Q3_K_M (19GB with 8K context, ~125 tokens/sec). Our top all-round pick for it is Qwen3.8 27B (Q4_K_M, ~36 tokens/sec).

## Key specs

- Memory: 24GB GDDR6
- Memory bandwidth: 960 GB/s
- Architecture: RDNA 3 (2022)
- Power: 355W
- Typical price: ~$1,050 used (checked 2026-10)
- Software: ROCm, Vulkan

## Best models for this GPU

- **Best overall (also coding, reasoning, vision):** Qwen3.8 27B at Q4_K_M, ~18.1GB with 8K context, ~36 tokens/sec
- **Runner-up:** Gemma 4 31B at Q4_K_M, ~22.5GB with 8K context, ~30 tokens/sec
- **Fastest good model (also largest that fits):** Qwen3.6 35B-A3B at Q3_K_M, ~19.2GB with 8K context, ~125 tokens/sec

## Compatibility (best quantization that fits, 8K context)

| Model | Params | Quant | Memory | Speed | Verdict |
| --- | --- | --- | --- | --- | --- |
| Gemma 4 E4B | 8B | Q8_0 | 10.5GB | ~60 tok/s | Runs well |
| Qwen3.5 9B | 9B | Q8_0 | 12.0GB | ~53 tok/s | Runs well |
| Phi-4 | 14.7B | Q8_0 | 18.3GB | ~38 tok/s | Runs well |
| gpt-oss-20b | 20.9B (3.6B active) | MXFP4 | 15.0GB | ~99 tok/s | Runs well |
| Gemma 4 26B A4B | 26B (3.8B active) | Q5_K_M | 20.1GB | ~91 tok/s | Runs well |
| Qwen3.8 27B | 27B | Q4_K_M | 18.1GB | ~36 tok/s | Runs well |
| Gemma 4 31B | 31B | Q4_K_M | 22.5GB | ~30 tok/s | Fits, tight |
| Qwen3.6 35B-A3B | 35B (3B active) | Q3_K_M | 19.2GB | ~125 tok/s | Runs well |
| GLM-4.5-Air | 106B (12B active) | Q4_K_M | 68.3GB | ~8.2 tok/s | Partial offload |
| Llama 4 Scout | 109B (17B active) | Q4_K_M | 69.5GB | ~5.8 tok/s | Partial offload |
| gpt-oss-120b | 117B (5.1B active) | MXFP4 | 68.3GB | ~20 tok/s | Partial offload |
| Qwen3.5 122B-A10B | 122B (10B active) | - | - | - | Won't fit |
| DeepSeek V4 Flash | 284B (13B active) | - | - | - | Won't fit |
| GLM-5.3-Flash | 320B (18B active) | - | - | - | Won't fit |
| GLM-5.3 | 744B (40B active) | - | - | - | Won't fit |

## Pros
- 24GB with 960 GB/s bandwidth
- Official ROCm support and strong Vulkan performance
- Open-source Linux drivers

## Cons
- Slower prompt processing than comparable NVIDIA cards
- Some tools and quantization formats are CUDA-only
- Used prices above launch MSRP

Full page: https://llamabuilds.ai/gpus/rx-7900-xtx · Best models: https://llamabuilds.ai/gpus/rx-7900-xtx/best-models

Sources: [Wikipedia, Radeon RX 7000 series](https://en.wikipedia.org/wiki/Radeon_RX_7000_series), [CPUTronic RX 7900 XTX specifications](https://cputronic.com/en/gpu/amd-radeon-rx-7900-xtx)

---
Source: https://llamabuilds.ai/gpus/rx-7900-xtx · Updated October 14, 2026 · Llama Builds. Speeds marked ~ are estimates from our bandwidth model (https://llamabuilds.ai/methodology); measured results are labeled as such.