RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek R1 Distill Llama 8B run on the RTX A6000?

Yes. At 8K context the best fit is F16, using about 31.6 GB of the 45.6 GB usable on the RTX A6000. Estimated speed ceiling: ~24 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •4.1 GB Fits4.6 GB Fits7.6 GB Fits19.6 GB Fits242
3-bit (Q3_K_M) •4.9 GB Fits5.4 GB Fits8.4 GB Fits20.4 GB Fits191
4-bit (Q4_K_M) •5.7 GB Fits6.2 GB Fits9.2 GB Fits21.2 GB Fits156
5-bit (Q5_K_M) •6.5 GB Fits7.0 GB Fits10.0 GB Fits22.0 GB Fits134
6-bit (Q6_K) •7.3 GB Fits7.8 GB Fits10.8 GB Fits22.8 GB Fits116
8-bit (Q8_0) •9.1 GB Fits9.6 GB Fits12.6 GB Fits24.6 GB Fits90
16-bit (F16/BF16) •31.1 GB Fits31.6 GB Fits34.6 GB Fits46.6 GB No24

• real GGUF file size from unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF. Speed is a bandwidth ceiling (768 GB/s), not a benchmark. Methodology.

More

DeepSeek R1 Distill Llama 8B on every GPU and Mac · Every model that runs on the RTX A6000 · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/DeepSeek-R1-Distill-Llama-8B), NVIDIA specs. Data as of 2026-11-17.