Can I Run Command R Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Newer alternative. Cohere has not released a newer model in this library. If you are choosing today, Mistral Small 4 is a comparable current option.
View Mistral Small 4 →
Written by Jakub Rusinowski · Last updated April 4, 2024
Yes, but it is tight
Yes, but it is tight — Command R (35B) at Q2_K needs about 23 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1 GB before the runtime starts swapping. Expect ~40.7 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: medium · Recommended quantization: Q2_K · Estimated speed: ~40.7 tok/s
RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model
| Usable memory for models | 24 GB |
| Memory bandwidth | 1008 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
Command R Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization
| Quant | Memory needed | Fits 24 GB? | Max context | Est. speed | Download |
|---|
| F16 | 81.5 GB | ✗ No | — | — | 70 GB |
| Q8_0 | 48.7 GB | ✗ No | — | — | 37.2 GB |
| Q6_K | 40.2 GB | ✗ No | — | — | 28.7 GB |
| Q5_K_M | 36.3 GB | ✗ No | — | — | 24.8 GB |
| Q4_K_M | 32.7 GB | ✗ No | — | — | 21.1 GB |
| Q3_K_M | 26.5 GB | ✗ No | — | — | 14.9 GB |
| Q2_K | 23 GB | ✓ Yes | 8K | ~40.7 tok/s | 11.5 GB |
Which Command R Family sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|
| Command R+ (104B) | 65.7 GB | ✗ Too large | — |
| Command R (35B) | 32.7 GB | ✗ Too large | — |
What to watch out for
- Only ~1 GB of headroom at Q2_K: a longer context or a second application can push this into swapping.
- Q2_K is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
- 2 larger variants of Command R Family do not fit and would need CPU offload or different hardware.
RTX 4090 desktop limitations
- 24 GB is the sweet spot for 27–32B models at Q4; 70B needs offload or a second card.
Recommended setup
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 24 GB of VRAM on the NVIDIA GeForce RTX 4090 at 1008 GB/s.
- 64 GB of system RAM available for CPU offload when a model exceeds VRAM.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run Command R Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Yes, but it is tight — Command R (35B) at Q2_K needs about 23 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1 GB before the runtime starts swapping. Expect ~40.7 tok/s (estimated), with room for about 8,192 tokens of context.
Which quantization of Command R Family should I use on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Q2_K — it needs about 23 GB of the 24 GB available, downloads as roughly 11.5 GB, and runs at an estimated 40.7 tokens/sec with up to 8K of context.
What limits Command R Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Computers
Other Models on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
Command R Family on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Command R Family model page | Check your hardware