RTX PRO 6000 Blackwell Workstation Edition 96GBコスパ重視96 GB VRAM (+16)
A
This setup is broadly balanced for this model.25.8 tok/sデコード
〜$9,999 MSRP
Can Command R+ 104B run on NVIDIA H800 80GB?
YES — Tight Fit
B69Good
Estimated from fit model
Command R+ 104B needs ~75.8 GB VRAM. NVIDIA H800 80GB has 80.0 GB. With Q4_K_M quantization, expect ~42 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: HighStack: StandardBottleneck: Balanced
Operating mode
Choose the run profile you care about
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Q4_K_M (Medium quality) — 75.8 GB, 41.7 tok/s, Tight fit
75.8 GB required80.0 GB available
95% VRAM used
Fit status
Tight fit
Decode
41.7 tok/s
TTFT
4648 ms
Safe context
36K
Memory
75.8 GB / 80.0 GB
Memory breakdown
Weights63.4 GB
KV Cache3.4 GB
Runtime0.9 GB
Headroom8.0 GB
See how fast it feels
See how fast it feelsCommand R+ 104B on NVIDIA H800 80GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.
Given information:
- Speed = 60 mph (miles per hour)
- Time = 2.5 hours
Formula: Distance = Speed x Time
Calculation:
Distance = 60 mph x 2.5 h
= 150 miles
The train travels 150 miles.
Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.
Breakdown:
- First half: 1.25 hours at 60 mph = 75 miles
- Stop: 20 minutes (no distance)
- Second half: 1.25 hours at 60 mph = 75 miles
Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph
The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 41.7 tok/s decode · 4.6s TTFT (warm) · 104 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Best improvement path
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Tight fit | 41.7 tok/s | 2535 ms | 36K |
| Coding | B | Tight fit | 41.7 tok/s | 4648 ms | 36K |
| Agentic Coding | B | Runs with offload | 41.7 tok/s | 6760 ms | 36K |
| Reasoning | B | Tight fit | 41.7 tok/s | 5493 ms | 36K |
| RAG | B | Runs with offload | 41.7 tok/s | 8450 ms | 36K |
Quantization options
How Command R+ 104B (104B params) fits at each quantization level on NVIDIA H800 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 40.6 GB | Low | B65 |
Q3_K_S | 3 | 51.0 GB | Low | B65 |
NVFP4 | 4 | 58.2 GB | Medium | B65 |
Q4_K_MBest for your GPU | 4 | 63.4 GB | Medium | B65 |
Q5_K_M | 5 | 74.9 GB | High | F0 |
Q6_K | 6 | 85.3 GB | High | F0 |
Q8_0 | 8 | 111.3 GB | Very High | F0 |
F16 | 16 | 213.2 GB | Maximum | F0 |
Get started
Copy-paste commands to run Command R+ 104B on your machine.
Run
ollama run command-r-plusアップグレードオプション
Command R+ 104Bを快適に動かすハードウェア
RTX PRO 6000 Blackwell Workstation Edition 96GBコスパ重視RTX PRO 6000 Blackwell Server Edition 96GBコスパ最良96 GB VRAM (+16)
B
This setup is broadly balanced for this model.23 tok/sデコード
〜$9,999 MSRP
NVIDIA H20 96GBNVIDIAアップグレード96 GB VRAM (+16)4000 GB/s (+1000)
A
Raises estimated decode speed by about 33%.55.5 tok/sデコード
Raises estimated decode speed by about 33%.
〜$12,000 MSRP
Frequently asked questions
Can NVIDIA H800 80GB run Command R+ 104B?
Yes, NVIDIA H800 80GB can run Command R+ 104B with a B grade (Tight fit). Expected decode speed: 41.7 tok/s.
How much VRAM does Command R+ 104B need?
Command R+ 104B (104B parameters) requires approximately 75.8 GB of memory with Q4_K_M quantization.
What is the best quantization for Command R+ 104B?
The recommended quantization for Command R+ 104B is Q4_K_M, which balances quality and memory efficiency.
What speed will Command R+ 104B run at on NVIDIA H800 80GB?
On NVIDIA H800 80GB, Command R+ 104B achieves approximately 41.7 tokens per second decode speed with a time-to-first-token of 4648ms using Q4_K_M quantization.
Can NVIDIA H800 80GB run Command R+ 104B for coding?
For coding workloads, Command R+ 104B on NVIDIA H800 80GB receives a B grade with 41.7 tok/s and 36K context.
What context window can Command R+ 104B use on NVIDIA H800 80GB?
On NVIDIA H800 80GB, Command R+ 104B can safely use up to 36K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
What should I upgrade first if Command R+ 104B feels slow on NVIDIA H800 80GB?
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/command-r-plus-104b-on-h800-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: