Command R+ 104B needs ~93.4 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q4_K_M quantization, expect ~75 tok/s.
Operating mode
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
Fit status
Runs well
Decode
75.1 tok/s
TTFT
2578 ms
Safe context
131K
Memory
93.4 GB / 256.0 GB
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 75.1 tok/s | 1406 ms | 131K |
| Coding | B | Runs well | 75.1 tok/s | 2578 ms | 131K |
| Agentic Coding | B | Runs well | 75.1 tok/s | 3751 ms | 131K |
| Reasoning | B | Runs well | 75.1 tok/s | 3047 ms | 131K |
| RAG | B | Runs well | 75.1 tok/s | 4688 ms | 131K |
How Command R+ 104B (104B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 40.6 GB | Low | B56 |
Q3_K_S | 3 | 51.0 GB | Low | B57 |
NVFP4 | 4 | 58.2 GB | Medium | B58 |
Q4_K_M | 4 | 63.4 GB | Medium | B58 |
Q5_K_M | 5 | 74.9 GB | High | B59 |
Q6_K | 6 | 85.3 GB | High | B60 |
Q8_0 | 8 | 111.3 GB | Very High | B62 |
F16Best for your GPU | 16 | 213.2 GB | Maximum | B65 |
Copy-paste commands to run Command R+ 104B on your machine.
Run
ollama run command-r-plusYes, AMD Instinct MI325X 256GB can run Command R+ 104B with a B grade (Runs well). Expected decode speed: 75.1 tok/s.
Command R+ 104B (104B parameters) requires approximately 93.4 GB of memory with Q4_K_M quantization.
The recommended quantization for Command R+ 104B is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI325X 256GB, Command R+ 104B achieves approximately 75.1 tokens per second decode speed with a time-to-first-token of 2578ms using Q4_K_M quantization.
For coding workloads, Command R+ 104B on AMD Instinct MI325X 256GB receives a B grade with 75.1 tok/s and 131K context.
On AMD Instinct MI325X 256GB, Command R+ 104B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/command-r-plus-104b-on-instinct-mi325x-256gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: