Can DeepSeek V4.1 Flash 1017 run on the RTX 3080 10GB?
Yes. At 8K context the best fit is F16, using about 9.3 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~363 tokens/sec.
Newer compressed-attention design: long-context figures are an upper bound.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 268 GB No | 268 GB No | 270 GB No | 278 GB No | — |
| 3-bit (Q3_K_M) | 348 GB No | 349 GB No | 351 GB No | 359 GB No | — |
| 4-bit (Q4_K_M) | 435 GB No | 436 GB No | 438 GB No | 446 GB No | — |
| 5-bit (Q5_K_M) | 507 GB No | 508 GB No | 510 GB No | 518 GB No | — |
| 6-bit (Q6_K) | 584 GB No | 584 GB No | 586 GB No | 595 GB No | — |
| 8-bit (Q8_0) • | 8.4 GB Fits | 8.8 GB Tight | 10.9 GB No | 19.3 GB No | 387 |
| 16-bit (F16/BF16) • | 8.9 GB Tight | 9.3 GB Tight | 11.4 GB No | 19.8 GB No | 363 |
• real GGUF file size from unsloth/DeepSeek-V4.1-Flash-1017-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs DeepSeek V4.1 Flash 1017: Arc B580 (12 GB, launch MSRP $249) at F16, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 3080 10GB: KORMo Web 11B (11B) at Q4_K_M, about 8.3 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
DeepSeek V4.1 Flash 1017 on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (deepseek-ai/DeepSeek-V4.1-Flash-1017), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.