B79.3 tok/s decode
Can it run?
Runs well
Using Q4_K_M in vLLM
Fit status
Runs well
Decode
35.9 tok/s
TTFT
5390 ms
Safe context
4K
Memory
61.7 GB / 80.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 41.9 tok/s | 6720 ms | 4K |
| Chat | C | Runs well | 41.9 tok/s | 2520 ms | 4K |
| Coding | C | Runs well | 35.9 tok/s | 5390 ms | 4K |
| RAG | C | Tight fit | 41.9 tok/s | 8399 ms | 4K |
| Reasoning | C | Runs well | 41.9 tok/s | 5460 ms | 4K |
How DeepSeek LLM 67B (67B params) fits at each quantization level on NVIDIA A100 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 26.1 GB | Low | D36 |
Q3_K_S | 3 | 32.8 GB | Low | D38 |
NVFP4 | 4 |
ollama run deepseek-llm-67bhuggingface-cli download deepseek-llm-67bUpgrade options
37.5 GB |
| Medium |
| D39 |
Q4_K_M | 4 | 40.9 GB | Medium | D40 |
Q5_K_M | 5 | 48.2 GB | High | C42 |
Q6_KBest for your GPU | 6 | 54.9 GB | High | C44 |
Q8_0 | 8 | 71.7 GB | Very High | C44 |
F16 | 16 | 137.4 GB | Maximum | F0 |