Can DeepSeek V3.2 run on the 2x RTX 3090?
No. Even at 2-bit with 8K context, DeepSeek V3.2 needs about 230 GB, more than the 45.6 GB usable on the 2x RTX 3090.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 229 GB No | 230 GB No | 232 GB No | 240 GB No | — |
| 3-bit (Q3_K_M) • | 299 GB No | 300 GB No | 302 GB No | 309 GB No | — |
| 4-bit (Q4_K_M) • | 379 GB No | 379 GB No | 381 GB No | 389 GB No | — |
| 5-bit (Q5_K_M) • | 444 GB No | 445 GB No | 447 GB No | 455 GB No | — |
| 6-bit (Q6_K) • | 514 GB No | 515 GB No | 517 GB No | 525 GB No | — |
| 8-bit (Q8_0) • | 665 GB No | 666 GB No | 668 GB No | 675 GB No | — |
| 16-bit (F16/BF16) • | 1251 GB No | 1251 GB No | 1253 GB No | 1261 GB No | — |
• real GGUF file size from unsloth/DeepSeek-V3.2-GGUF. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.
Hardware that does fit it
More
DeepSeek V3.2 on every GPU and Mac · Every model that runs on the 2x RTX 3090 · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/DeepSeek-V3.2), NVIDIA specs. Data as of 2026-11-17.