Can DeepSeek R1 Distill Llama 70B run on the RTX 6000 Ada?
Yes. At 8K context the best fit is Q3_K_M, using about 35.1 GB of the 45.6 GB usable on the RTX 6000 Ada. Estimated speed ceiling: ~28 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 26.5 GB Fits | 27.7 GB Fits | 35.2 GB Fits | 65.2 GB No | 36 |
| 3-bit (Q3_K_M) • | 33.8 GB Fits | 35.1 GB Fits | 42.6 GB Tight | 72.6 GB No | 28 |
| 4-bit (Q4_K_M) • | 41.5 GB Tight | 42.7 GB Tight | 50.2 GB No | 80.2 GB No | 23 |
| 5-bit (Q5_K_M) • | 48.4 GB No | 49.7 GB No | 57.2 GB No | 87.2 GB No | — |
| 6-bit (Q6_K) • | 110 GB No | 111 GB No | 118 GB No | 148 GB No | — |
| 8-bit (Q8_0) • | 71.7 GB No | 73.0 GB No | 80.5 GB No | 110 GB No | — |
| 16-bit (F16/BF16) • | 265 GB No | 266 GB No | 273 GB No | 303 GB No | — |
• real GGUF file size from unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs DeepSeek R1 Distill Llama 70B: 2x RTX 5090 (2× 32 GB, launch MSRP $3,998) at Q5_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 6000 Ada: DeepSeek V4 Flash 0731 (304B, MoE) at F16, about 11.9 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 R1 Distill Llama 70B on every GPU and Mac · Every model that runs on the RTX 6000 Ada · Other models that fit 48 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-R1-Distill-Llama-70B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.