DeepSeek on AMD RDNA3
Can I run DeepSeek-R1 671B-A37B on an Radeon RX 7900 XTX?
Not at Q4_K_M — it needs 380.4 GB against 21.8 GB available. No quantisation of this model fits on one card.
Won't fit
380.4 GB of 21.8 GB · 1748%0396 GB
Weights
379.0 GB
KV cache
0.5 GB
Runtime overhead
0.9 GB
Over the limit
358.6 GB
Short by 358.6 GB. You can run it with 3 of 61 layers on the Radeon RX 7900 XTX and the rest in system RAM, at roughly 1.78 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation1.78tok/s
Prompt processing698tok/s
Max context0tokens
KV per 1K tokens0GB
Every quantisation of DeepSeek-R1 671B-A37B on a Radeon RX 7900 XTX
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 1249.8 GB | 1251.2 GB | Won't fit | — | 0.52 |
| INT8 / W8A8 | 8.50 | 663.6 GB | 665.0 GB | Won't fit | — | 1.00 |
| Q8_0 (GGUF) | 8.50 | 663.6 GB | 665.0 GB | Won't fit | — | 1.00 |
| FP8 (E4M3) | 8.00 | 624.9 GB | 626.3 GB | Won't fit | — | 1.06 |
| Q6_K | 6.56 | 512.4 GB | 513.8 GB | Won't fit | — | 1.30 |
| Q5_K_M | 5.67 | 442.9 GB | 444.3 GB | Won't fit | — | 1.51 |
| Q5_K_S | 5.52 | 431.2 GB | 432.6 GB | Won't fit | — | 1.55 |
| Q4_K_M | 4.85 | 379.0 GB | 380.4 GB | Won't fit | — | 1.78 |
| Q4_K_S | 4.58 | 358.0 GB | 359.4 GB | Won't fit | — | 1.88 |
| Q4_0 | 4.55 | 355.6 GB | 357.0 GB | Won't fit | — | 1.90 |
| AWQ 4-bit | 4.25 | 334.5 GB | 335.9 GB | Won't fit | — | 2.01 |
| GPTQ 4-bit | 4.25 | 334.5 GB | 335.9 GB | Won't fit | — | 2.01 |
| MXFP4 | 4.25 | 334.5 GB | 335.9 GB | Won't fit | — | 2.01 |
| IQ4_XS | 4.25 | 332.3 GB | 333.7 GB | Won't fit | — | 2.03 |
| Q3_K_M | 3.91 | 305.8 GB | 307.2 GB | Won't fit | — | 2.23 |
| IQ3_M | 3.70 | 289.4 GB | 290.8 GB | Won't fit | — | 2.35 |
| IQ3_XXS | 3.06 | 239.6 GB | 241.0 GB | Won't fit | — | 2.87 |
| Q2_K | 2.63 | 206.1 GB | 207.5 GB | Won't fit | — | 3.37 |
| IQ2_XXS | 2.06 | 161.7 GB | 163.1 GB | Won't fit | — | 4.32 |
| IQ1_M | 1.75 | 137.5 GB | 138.9 GB | Won't fit | — | 5.21 |