Can DeepSeek R1 Distill 8B run on RX 6800 XT 16GB?
YES — Runs Great
DeepSeek R1 Distill 8B needs ~9.3 GB VRAM. RX 6800 XT 16GB has 16.0 GB. With Q4_K_M quantization, expect ~63 tok/s.
Operating mode
Choose the run profile you care about
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
63.2 tok/s
TTFT
3065 ms
Safe context
33K
Memory
9.3 GB / 16.0 GB
Memory breakdown
See how fast it feels
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 63.2 tok/s | 1672 ms | 33K |
| Coding | B | Runs well | 63.2 tok/s | 3065 ms | 33K |
| Agentic Coding | A | Runs well | 63.2 tok/s | 4458 ms | 33K |
| Reasoning | B | Runs well | 63.2 tok/s | 3623 ms | 33K |
| RAG | A | Runs well | 63.2 tok/s | 5573 ms | 33K |
Quantization options
How DeepSeek R1 Distill 8B (8B params) fits at each quantization level on RX 6800 XT 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | B64 |
Q3_K_S | 3 | 3.9 GB | Low | B64 |
NVFP4 | 4 |
Get started
Copy-paste commands to run DeepSeek R1 Distill 8B on your machine.
Run
ollama run deepseek-r1:8b