Can I Run Command R+ (104B) on NVIDIA L40S?
Written by Jakub Rusinowski · Last updated July 21, 2026
Not at Q4_K_M — that needs 65.7 GB at 8K context and the NVIDIA L40S has 48 GB. Drop to Q3_K_M and it fits in 47.3 GB, with up to 8K of context.
Get a personalized upgrade path →
The numbers
| Model | Command R+ (104B) |
| Parameters | 104B |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 65.7 GB |
| NVIDIA L40S VRAM | 48 GB |
| Verdict | Runs at a lower quant |
| Fits at | Q3_K_M (47.3 GB) |
| Max context | 8K |
Command R+ (104B) on the NVIDIA L40S: VRAM by quantization
| Quant | VRAM needed | Fits 48 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 210.9 GB | ✗ No | — | — |
| Q8_0 | 113.4 GB | ✗ No | — | — |
| Q6_K | 88.2 GB | ✗ No | — | — |
| Q5_K_M | 76.7 GB | ✗ No | — | — |
| Q4_K_M | 65.7 GB | ✗ No | — | — |
| Q3_K_M | 47.3 GB | ✓ Yes | 8K | — |
| Q2_K | 37.1 GB | ✓ Yes | 32K | — |
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 65.7 GB ✗ · 32K 72.2 GB ✗ · 125K 97.1 GB ✗. Past 8K it no longer fits 48 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Quantize to Q3_K_M. That is the cheapest fix — it costs some quality but no money.
No compatible GPU? Command R+ (104B) on 256 GB of system RAM, CPU only: runs, but too slowly to be worth it.
Running Command R+ (104B) on this card:
Command R+ (104B) needs ~66 GB but this GPU has 48 GB. Rent a A100 (80 GB)-class GPU by the hour instead of buying one:
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.
Other Command R Family sizes on the NVIDIA L40S
- Command R (35B) — runs (32.7 GB)
Command R+ (104B) on nearby hardware
- Apple M3 Pro (36 GB) — does not fit
- NVIDIA A100 80GB (PCIe) (80 GB) — runs
All Command R Family sizes on the NVIDIA L40S | Command R+ (104B) model page | NVIDIA L40S GPU page | VRAM calculator | Check your hardware