141 GB VRAM (+13)4800 GB/s (+1600)
A
Raises estimated decode speed by about 85%.69.1 tok/s decode
Raises estimated decode speed by about 85%.
~$30,000 MSRP
Can Command R+ 104B run on AMD Instinct MI250 128GB?
YES — Runs Great
B70Good
○Estimated from fit model
Command R+ 104B needs ~80.6 GB VRAM. AMD Instinct MI250 128GB has 128.0 GB. With Q4_K_M quantization, expect ~37 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced
Share:
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) — 80.6 GB, 37.3 tok/s, Runs well
80.6 GB required128.0 GB available
63% VRAM used
Fit status
Runs well
Decode
37.3 tok/s
TTFT
5190 ms
Safe context
131K
Memory
80.6 GB / 128.0 GB
Memory breakdown
Weights63.4 GB
KV Cache3.4 GB
Runtime0.9 GB
Headroom12.8 GB
See how fast it feels
See how fast it feelsCommand R+ 104B on AMD Instinct MI250 128GB
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: 37.3 tok/s decode · 5.2s TTFT (warm) · 93 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 37.3 tok/s | 2831 ms | 131K |
| Coding | B | Runs well | 37.3 tok/s | 5190 ms | 131K |
| Agentic Coding | A | Runs well | 37.3 tok/s | 7549 ms | 131K |
| Reasoning | B | Runs well | 37.3 tok/s | 6134 ms | 131K |
| RAG | A | Runs well | 37.3 tok/s | 9437 ms | 131K |
Quantization options
How Command R+ 104B (104B params) fits at each quantization level on AMD Instinct MI250 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 40.6 GB | Low | B60 |
Q3_K_S | 3 | 51.0 GB | Low | B62 |
NVFP4 | 4 | 58.2 GB | Medium | B63 |
Q4_K_M | 4 | 63.4 GB | Medium | B64 |
Q5_K_M | 5 | 74.9 GB | High | B65 |
Q6_KBest for your GPU | 6 | 85.3 GB | High | B65 |
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-plusUpgrade options