RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can DeepSeek R1 Distill Qwen 32B run on the L40S?

Yes. At 8K context the best fit is Q8_0, using about 35.1 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~25 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •13.2 GB Fits14.2 GB Fits20.2 GB Fits44.2 GB Tight70
3-bit (Q3_K_M) •16.5 GB Fits17.5 GB Fits23.5 GB Fits47.5 GB No54
4-bit (Q4_K_M) •20.2 GB Fits21.2 GB Fits27.2 GB Fits51.2 GB No44
5-bit (Q5_K_M) •23.4 GB Fits24.4 GB Fits30.4 GB Fits54.4 GB No37
6-bit (Q6_K) •26.7 GB Fits27.7 GB Fits33.7 GB Fits57.7 GB No32
8-bit (Q8_0) •34.1 GB Fits35.1 GB Fits41.1 GB Tight65.1 GB No25
16-bit (F16/BF16) •62.7 GB No63.7 GB No69.7 GB No93.7 GB No—

• real GGUF file size from bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.

What fits instead

"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 Qwen 32B on every GPU and Mac · Every model that runs on the L40S · 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-Qwen-32B), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.