Can I Run Command R Family on NVIDIA L40S?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
Yes, comfortably — Command R (35B) at Q4_K_M needs 32.7 GB at 8K context (21.1 GB weights + 11.6 GB KV cache/overhead), leaving ~15.3 GB of the NVIDIA L40S's 48 GB, at ~28 tok/s (est.), with room for up to 16K context.
See what else this hardware can run →
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
NVIDIA L40S Specs
| VRAM | 48 GB |
| Memory Bandwidth | 864 GB/s |
Command R (35B) on the NVIDIA L40S: VRAM by quantization
| Quant | VRAM needed | Fits 48 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 81.5 GB | ✗ No | — | — |
| Q8_0 | 48.7 GB | ✗ No | — | — |
| Q6_K | 40.2 GB | ✓ Yes | 8K | — |
| Q5_K_M | 36.3 GB | ✓ Yes | 16K | — |
| Q4_K_M | 32.7 GB | ✓ Yes | 16K | — |
| Q3_K_M | 26.5 GB | ✓ Yes | 16K | — |
| Q2_K | 23 GB | ✓ Yes | 16K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 48 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA L40S: 8K 32.7 GB · 32K 64.9 GB ✗ · 125K 189.7 GB ✗. Past 32K it no longer fits 48 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Command R Family on 256 GB of system RAM, CPU only: runs, but too slowly to be worth it.
Command R Family Sizes That Fit the NVIDIA L40S (at 8K context)
| Command R (35B) | Q4_K_M · 32.7 GB at 8K context · ~28 tok/s (est.) |
At 2 hrs/day, buying (~$7,499) beats renting at $0.55/hr after about 18.9 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Can I run Command R Family on the NVIDIA L40S?
Yes, comfortably — Command R (35B) at Q4_K_M needs 32.7 GB at 8K context (21.1 GB weights + 11.6 GB KV cache/overhead), leaving ~15.3 GB of the NVIDIA L40S's 48 GB, at ~28 tok/s (est.), with room for up to 16K context.
What's the best Command R Family size for the NVIDIA L40S?
Command R (35B) at Q4_K_M quantization needs 32.7 GB at 8K context (21.1 GB weights + 11.6 GB KV cache/overhead), estimated ~28 tokens/sec, up to 16K context.
Every Command R Family size on the NVIDIA L40S
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| Command R+ (104B) | 65.7 GB | Runs at Q3_K_M | — |
| Command R (35B) | 32.7 GB | Runs | ~28 tok/s |
Command R Family on Other GPUs
- Command R Family on NVIDIA RTX 6000 Ada Generation
- Command R Family on Apple M3 Pro
- Command R Family on NVIDIA GeForce RTX 5090
- Command R Family on Apple M4
- Command R Family on Apple M2 Pro
Popular Models on the NVIDIA L40S
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | Command R Family Model Page | NVIDIA L40S GPU Page | VRAM calculator | Check Your Hardware