Can it run?
Runs well
Using Q4_K_M in llama.cpp
Fit status
Runs well
Decode
61.2 tok/s
TTFT
3164 ms
Safe context
20K
Memory
31.7 GB / 40.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 61.2 tok/s | 4603 ms | 34K |
| Chat | B | Runs well | 61.2 tok/s | 1726 ms | 11K |
| Coding | B | Runs well | 61.2 tok/s | 3164 ms | 20K |
| RAG | C | Tight fit | 61.2 tok/s | 5753 ms | 34K |
| Reasoning | B | Runs well | 61.2 tok/s | 3740 ms | 20K |
How Command R 35B (35B params) fits at each quantization level on NVIDIA A100 40GB (40.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | D37 |
Q3_K_S | 3 | 17.2 GB | Low | D38 |
NVFP4 | 4 | 19.6 GB | Medium | D40 |
Q4_K_M | 4 | 21.3 GB | Medium | C41 |
Q5_K_M | 5 | 25.2 GB | High | C43 |
Q6_KBest for your GPU | 6 | 28.7 GB | High | C44 |
Q8_0 | 8 | 37.5 GB | Very High | C44 |
F16 | 16 | 71.8 GB | Maximum | F0 |
ollama run command-r-35bhuggingface-cli download command-r-35b