Can I Run Command R+ (104B) on NVIDIA H100 80GB (PCIe)?
Written by Jakub Rusinowski · Last updated July 21, 2026
Yes. Command R+ (104B) needs 65.7 GB at 8K context (62.8 GB weights + 2.9 GB KV cache/overhead) at Q4_K_M and the NVIDIA H100 80GB (PCIe) has 80 GB, leaving about 14.3 GB of headroom, at roughly 25 tok/s (estimated) with room for up to 32K of context.
See what else this hardware can run →
The numbers
| Model | Command R+ (104B) |
| Parameters | 104B |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 65.7 GB |
| NVIDIA H100 80GB (PCIe) VRAM | 80 GB |
| Verdict | Runs |
| Max context | 32K |
| Estimated speed | ~25 tok/s |
Command R+ (104B) on the NVIDIA H100 80GB (PCIe): VRAM by quantization
| Quant | VRAM needed | Fits 80 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 | ✓ Yes | 16K | — |
| Q4_K_M | 65.7 GB | ✓ Yes | 32K | — |
| Q3_K_M | 47.3 GB | ✓ Yes | 64K | — |
| Q2_K | 37.1 GB | ✓ Yes | 64K | — |
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 80 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 H100 80GB (PCIe): 8K 65.7 GB · 32K 72.2 GB · 125K 97.1 GB ✗. Past 125K it no longer fits 80 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
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:
At 2 hrs/day, buying (~$25,000) beats renting at $0.77/hr after about 45.1 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.
Other Command R Family sizes on the NVIDIA H100 80GB (PCIe)
- Command R (35B) — runs (32.7 GB)
Command R+ (104B) on nearby hardware
- NVIDIA L40S (48 GB) — runs at a lower quant
- Apple M2 Max (96 GB) — runs
All Command R Family sizes on the NVIDIA H100 80GB (PCIe) | Command R+ (104B) model page | NVIDIA H100 80GB (PCIe) GPU page | VRAM calculator | Check your hardware