With 80 GB of VRAM, the A100 80GB runs DeepSeek R1 Distill Qwen 32B at Q4_K_M entirely on the GPU with an 8K context (about 22.4 GB needed). At Q8_0 it fits entirely.
Q4_K_M · 8K context
The model needs about 22.4 GB and fits in the 77.6 GB available, with 55.2 GB to spare.
~22.4 GB (21.6 GB–23.2 GB) needed · estimate
Fits entirely in VRAM · 55.2 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| DeepSeek R1 Distill Qwen 32B Q8_08K~37 GB · 36–50 tok/s estimate | Excellent |
|---|---|
| DeepSeek R1 Distill Qwen 32B Q6_K8K~29.3 GB · 44–63 tok/s estimate | Excellent |
| DeepSeek R1 Distill Qwen 32B Q5_K_M8K~25.7 GB · 50–71 tok/s estimate | Excellent |
| DeepSeek R1 Distill Qwen 32B Q4_K_M8K~22.4 GB · 56–82 tok/s estimate | Excellent |
| DeepSeek R1 Distill Qwen 32B IQ4_XS8K~20.3 GB · 61–90 tok/s estimate | Excellent |
| DeepSeek R1 Distill Qwen 32B Q3_K_M8K~18.5 GB · 66–98 tok/s estimate | Excellent |
Prices and links follow the market you choose.
AMD
CompatibleRuns DeepSeek R1 Distill Qwen 32B Q4_K_M entirely in memory
Apple Silicon
CompatibleRuns DeepSeek R1 Distill Qwen 32B Q4_K_M entirely in memory
Unified memory PC
CompatibleRuns DeepSeek R1 Distill Qwen 32B Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
