Can it run?
Runs well
Using Q4_K_M in llama.cpp
Fit status
Runs well
Decode
31.6 tok/s
TTFT
6133 ms
Safe context
24K
Memory
32.5 GB / 48.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 31.6 tok/s | 8921 ms | 40K |
| Chat | C | Runs well | 31.6 tok/s | 3345 ms | 13K |
| Coding | C | Runs well | 31.6 tok/s | 6133 ms | 24K |
| RAG | C | Runs well | 31.6 tok/s | 11151 ms | 40K |
| Reasoning | C | Runs well | 31.6 tok/s | 7248 ms | 24K |
How Command R 35B (35B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | D35 |
Q3_K_S | 3 | 17.2 GB | Low | D37 |
NVFP4 | 4 | 19.6 GB | Medium | D38 |
Q4_K_M | 4 | 21.3 GB | Medium | D39 |
Q5_K_M | 5 | 25.2 GB | High | C40 |
Q6_K | 6 | 28.7 GB | High | C42 |
Q8_0Best for your GPU | 8 | 37.5 GB | Very High | C44 |
F16 | 16 | 71.8 GB | Maximum | F0 |
ollama run command-r-35bhuggingface-cli download command-r-35b