 |
VOOZH | about |
Command R+ 104B needs ~81.6 GB VRAM. Mac Studio M1 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~7 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
Tight fit
Decode
7.5 tok/s
TTFT
25668 ms
Safe context
66K
Memory
81.6 GB / 92.2 GB
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Tight fit | 6.9 tok/s | 15226 ms | 66K |
| Coding | B | Tight fit | 6.9 tok/s | 27914 ms | 66K |
| Agentic Coding | B | Tight fit | 6.9 tok/s | 40602 ms | 66K |
| Reasoning | B | Tight fit | 6.9 tok/s | 32989 ms | 66K |
| RAG | B | Tight fit | 6.9 tok/s | 50752 ms | 66K |
How Command R+ 104B (104B params) fits at each quantization level on Mac Studio M1 Ultra 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 40.6 GB | Low | B63 |
Q3_K_S | 3 | 51.0 GB | Low | B65 |
NVFP4 | 4 |
Copy-paste commands to run Command R+ 104B on your machine.
Run
ollama run command-r-plusUpgrade options
Raises estimated decode speed by about 1235%.
Adds memory headroom for longer context windows and future model growth.
~$8,000 MSRP
Raises estimated decode speed by about 244%.
Moves the workload away from shared memory into dedicated accelerator memory.
~$9,999 MSRP
58.2 GB |
| Medium |
| B65 |
Q4_K_M | 4 | 63.4 GB | Medium | B65 |
Q5_K_MBest for your GPU | 5 | 74.9 GB | High | B65 |
Q6_K | 6 | 85.3 GB | High | F0 |
Q8_0 | 8 | 111.3 GB | Very High | F0 |
F16 | 16 | 213.2 GB | Maximum | F0 |
Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
