Can the AMD Radeon RX 7900 XTX run DeepSeek R1 Distill Qwen 32B?
Yes
QuantQ4_K_MGood, most popular
Memory22.6 GBof 24 GB
Speed~29tokens/s
Yes. The AMD Radeon RX 7900 XTX can run DeepSeek R1 Distill Qwen 32B fully in VRAM at Q4_K_M (good, most popular), using about 22.6 GB of the 24 GB available, at roughly 29 tokens/second.
Try other context lengths in the calculator →Memory needed by quantization
At 8,192 tokens of context.
| Quant | Quality | Memory | Fits? | Speed |
|---|---|---|---|---|
| FP16 | Full quality | 68.3 GB | Too big | — |
| Q8_0 | Near-lossless | 37.6 GB | Too big | — |
| Q6_K | Excellent | 29.6 GB | Too big | — |
| Q5_K_M | Very good | 26.1 GB | Too big | — |
| Q4_K_M | Good, most popular | 22.6 GB | Fits | ~29 tok/s |
| Q3_K_M | Noticeably degraded | 18.8 GB | Fits | ~36 tok/s |
| Q2_K | Heavily degraded | 15 GB | Fits | ~47 tok/s |
How to run DeepSeek R1 Distill Qwen 32B on the AMD Radeon RX 7900 XTX
With Ollama installed, one command downloads and starts it:
ollama run deepseek-r1:32bOllama's default download is Q4_K_M (about 22.6 GB here). That is also the best quant that fits.
GPUs that run DeepSeek R1 Distill Qwen 32B comfortably
- NVIDIA RTX 3090 (24 GB)
- NVIDIA RTX 4090 (24 GB)
- NVIDIA RTX 5090 (32 GB)
- Apple M4 Pro (48GB)
- Apple M3 Max (64GB)
Models that run well on the AMD Radeon RX 7900 XTX
Run it in the cloud
Don't want to buy hardware? Run DeepSeek R1 Distill Qwen 32B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.